nips nips2011 nips2011-127 knowledge-graph by maker-knowledge-mining

127 nips-2011-Image Parsing with Stochastic Scene Grammar

Source: pdf

Author: Yibiao Zhao, Song-chun Zhu

Abstract: This paper proposes a parsing algorithm for scene understanding which includes four aspects: computing 3D scene layout, detecting 3D objects (e.g. furniture), detecting 2D faces (windows, doors etc.), and segmenting background. In contrast to previous scene labeling work that applied discriminative classiﬁers to pixels (or super-pixels), we use a generative Stochastic Scene Grammar (SSG). This grammar represents the compositional structures of visual entities from scene categories, 3D foreground/background, 2D faces, to 1D lines. The grammar includes three types of production rules and two types of contextual relations. Production rules: (i) AND rules represent the decomposition of an entity into sub-parts; (ii) OR rules represent the switching among sub-types of an entity; (iii) SET rules represent an ensemble of visual entities. Contextual relations: (i) Cooperative “+” relations represent positive links between binding entities, such as hinged faces of a object or aligned boxes; (ii) Competitive “-” relations represents negative links between competing entities, such as mutually exclusive boxes. We design an efﬁcient MCMC inference algorithm, namely Hierarchical cluster sampling, to search in the large solution space of scene conﬁgurations. The algorithm has two stages: (i) Clustering: It forms all possible higher-level structures (clusters) from lower-level entities by production rules and contextual relations. (ii) Sampling: It jumps between alternative structures (clusters) in each layer of the hierarchy to ﬁnd the most probable conﬁguration (represented by a parse tree). In our experiment, we demonstrate the superiority of our algorithm over existing methods on public dataset. In addition, our approach achieves richer structures in the parse tree. 1

Reference: text

Summary: the most important sentenses genereted by tfidf model

sentIndex sentText sentNum sentScore

1 edu Abstract This paper proposes a parsing algorithm for scene understanding which includes four aspects: computing 3D scene layout, detecting 3D objects (e. [sent-4, score-0.679]

2 In contrast to previous scene labeling work that applied discriminative classiﬁers to pixels (or super-pixels), we use a generative Stochastic Scene Grammar (SSG). [sent-8, score-0.266]

3 This grammar represents the compositional structures of visual entities from scene categories, 3D foreground/background, 2D faces, to 1D lines. [sent-9, score-1.038]

4 The grammar includes three types of production rules and two types of contextual relations. [sent-10, score-0.922]

5 Production rules: (i) AND rules represent the decomposition of an entity into sub-parts; (ii) OR rules represent the switching among sub-types of an entity; (iii) SET rules represent an ensemble of visual entities. [sent-11, score-0.785]

6 Contextual relations: (i) Cooperative “+” relations represent positive links between binding entities, such as hinged faces of a object or aligned boxes; (ii) Competitive “-” relations represents negative links between competing entities, such as mutually exclusive boxes. [sent-12, score-0.994]

7 We design an efﬁcient MCMC inference algorithm, namely Hierarchical cluster sampling, to search in the large solution space of scene conﬁgurations. [sent-13, score-0.308]

8 The algorithm has two stages: (i) Clustering: It forms all possible higher-level structures (clusters) from lower-level entities by production rules and contextual relations. [sent-14, score-0.947]

9 (ii) Sampling: It jumps between alternative structures (clusters) in each layer of the hierarchy to ﬁnd the most probable conﬁguration (represented by a parse tree). [sent-15, score-0.44]

10 In addition, our approach achieves richer structures in the parse tree. [sent-17, score-0.407]

11 By analogy to natural language parsing, we pose the scene understanding problem as parsing an image into a hierarchical structure of visual entities (in Fig. [sent-19, score-0.809]

12 The literature of scene parsing can be categorized into two categories: discriminative approaches and generative approaches. [sent-21, score-0.376]

13 Without an understanding of the scene structure, the pixel-level labeling is insufﬁcient to represent the knowledge of object occlusions, 3D relationships, functional space etc. [sent-24, score-0.302]

14 To address this problem, geometric descriptions were added to the scene interpretation. [sent-25, score-0.281]

15 edu/˜ybzhao/research/sceneparsing 1 (i) a parse tree scene 3D background 3D foregrounds (ii) input image and line detection 2D faces (iii) geometric parsing result 1D line segments (iv) reconstructed via line segments Figure 1: A parse tree of geometric parsing result. [sent-31, score-1.984]

16 Figure 2: 3D synthesis of novel views based on the parse tree. [sent-32, score-0.331]

17 [4] adopted different approaches to model the geometric layout of the background and/or foreground objects, and ﬁt their models into Structured SVM (or Latent SVM) settings [10]. [sent-40, score-0.341]

18 However, these discriminative approaches lack a general representation of visual vocabulary and a principled approach for exploring the compositional structure. [sent-43, score-0.245]

19 The stochastic grammar were used to parse natural languages [11]. [sent-45, score-0.63]

20 Zhu and Mumford [16] proposed an AND/OR Graph Model to represent the compositional structures in vision. [sent-47, score-0.212]

21 Han and Zhu [18] applied grammar rules, in a greedy manner, to detect rectangular structures in man-made scenes. [sent-50, score-0.34]

22 In this paper, we parse an image into a hierarchical structure, namely a parse tree as shown in Fig. [sent-54, score-0.836]

23 The parse tree covers a wide spectrum of visual entities, including scene categories, 3D foreground/background, 2D faces, and 1D line segments. [sent-56, score-0.711]

24 With the low-level information of the parse tree, we reconstruct the original image by the appearance of line segments, as shown in Fig. [sent-57, score-0.426]

25 With the high-level information of the parse tree, we further recover the 3D scene by the geometry of 3D background and foreground objects, as shown in Fig. [sent-59, score-0.748]

26 This paper has two major contributions to the scene parsing problems: (I) A Stochastic Scene Grammar (SSG) is introduced to represent the hierarchical structure of visual entities. [sent-61, score-0.467]

27 The grammar starts with a single root node (the scene) and ends with a set of terminal nodes (line segments). [sent-62, score-0.359]

28 In between, we generate all intermediate 3D/2D sub-structures by three types of production rules and two types of contextual relations, as illustrated in Fig. [sent-63, score-0.658]

29 For example, three hinged faces form a 3D box, four linked line segments form a rectangle, a background and inside objects form a scene in Fig. [sent-67, score-0.774]

30 a 3D foreground and 3D background have several switchable types in Fig. [sent-73, score-0.23]

31 (i) If the visual entities satisfy a cooperative “+” relation, they tend to bind together, e. [sent-76, score-0.552]

32 (ii) If entities satisfy a competitive “-” relation, they compete with each other for presence, e. [sent-80, score-0.374]

33 two exclusive foreground boxes competing for a same space in Fig. [sent-82, score-0.341]

34 The algorithm accelerates a Markov chain search by exploring contextual relations. [sent-85, score-0.23]

35 In each layer, the entities are ﬁrst ﬁltered by the Cooperative “+” constraints, they then form a cluster only if they satisfy the “+” constraints, e. [sent-89, score-0.393]

36 several faces form a cluster of a box when their edges are hinged tightly. [sent-91, score-0.435]

37 In summary, the Stochastic Scene Grammar is a general framework to parse a scene with a large number of geometric conﬁgurations. [sent-96, score-0.612]

38 P (r) = P (β|α) is an expansion probability for each production rule (r : α → β). [sent-99, score-0.28]

39 A set of all valid conﬁgurations C derived from production rules is called a language: {ri } L(G) = {C : S −−→ C, {ri } ⊂ R, C ⊂ V T , P ({ri }) > 0}. [sent-100, score-0.419]

40 We deﬁne three types of stochastic production rules RAN D ,ROR ,RSET to represent the structural regularity and ﬂexibility of visual entities. [sent-102, score-0.575]

41 3(i), the grammar outputs a high probability if the three faces of a 3D box are well hinged, and a low probability if the foreground box lays out of the background. [sent-108, score-0.679]

42 Moreover, OR rules also model the discrete size of entities, which is useful to rule out the extreme large or small entities. [sent-117, score-0.243]

43 The SET rule is equivalent to a mixture of OR and AND rules (rSET : A → ∅ | a | a · a | a · a · a | · · · ). [sent-119, score-0.243]

44 It ﬁrst chooses a set size k by ORing, and forms an ensemble of k entities by ANDing. [sent-120, score-0.308]

45 It is worth noting that the OR rule essentially changes the graph topology of the output parse tree by changing its node size k. [sent-121, score-0.447]

46 3(ii), the SET rule generates a set of 3D/2D entities which satisfy some contextual relations. [sent-123, score-0.53]

47 There are two kinds of contextual relations, Cooperative “+” relations and Competitive “-” relations, which involve in the AND and SET rules. [sent-125, score-0.393]

48 (i) The cooperative “+” relations specify the concurrent patterns in a scene, e. [sent-126, score-0.364]

49 The visual entities satisfying a cooperative “+” relation tend to bind together. [sent-130, score-0.56]

50 (i) The competitive “-” relations specify the exclusive patterns in a scene. [sent-131, score-0.379]

51 If entities satisfy competitive “-” relations, they compete with each other for the presence. [sent-132, score-0.374]

52 the loose structure: If several visual entities satisfy a cooperative “+” relation, they tend to bind together, and we call them tight structures. [sent-136, score-0.582]

53 If the entities neither satisfy any cooperative “+” relations nor violate a competitive “-” relation, they may be loosely combined. [sent-139, score-0.738]

54 With the three production rules and two contextual relations, SSG is able to handle an enormous number of conﬁgurations and large geometric variations, which are the major difﬁculties in our task. [sent-142, score-0.653]

55 3 Bayesian formulation of the grammar We deﬁne a posterior distribution for a solution (a parse tree) pt conditioned on an input image I. [sent-143, score-0.814]

56 This distribution is speciﬁed in terms of the statistics deﬁned over the derivation of production rules. [sent-144, score-0.228]

57 P (pt|I) ∝ P (pt)P (I|pt) = P (S) P (Chv |v) v∈V N P (I|v) (1) v∈V T where I is the input image, pt is the parse tree. [sent-145, score-0.489]

58 The probability derivation represents a generating process of the production rules {r : v → Chv } from the start symbol S to the nonterminal nodes v ∈ V N , and to the children of non-terminal nodes Chv . [sent-146, score-0.546]

59 The edge deﬁne a 4 (i) initial distribution (ii) with cooperative(+) relations (iii) with competitive(-) relations (iv) with both (+/-) relations Figure 4: Learning to synthesize. [sent-150, score-0.66]

60 The posterior distribution of a parse graph pt is given by a family of Gibbs distributions: P (pt|I; λ) = 1/Z(I; λ) exp{−E(pt|I)}, where Z(I; λ) = pt∈Ω exp{−E(pt|I)} is a partition function summation over the solution space Ω. [sent-153, score-0.489]

61 The switching probability of foreground objects and the u∈Ch(v) background layout is shown in Fig. [sent-157, score-0.396]

62 We deﬁne both “+” relations and “-” relations as E AN D = λ+ h+ (AG (Chv )) + λ− h− (AG (Chv )), where h(∗) are sufﬁcient statistics in the exponential model, λ are their parameters. [sent-161, score-0.44]

63 For 2D faces as an example, the “+” relation speciﬁes a quadratic distance between their connected joints h+ (AG (Chv )) = 2 a,b∈Chv (X(a) − X(b)) , and the “-” relation speciﬁes an overlap rate between their occupied image area h− (AG (Chv )) = (Λa ∩ Λb )/(Λa ∪ Λb ), a, b ∈ Chv . [sent-162, score-0.302]

64 The features used in this paper include: (a) surface labels of geometric context [1], (b) a 3D orientation map [21], (c) the MDL coding length of line segments [20]. [sent-164, score-0.231]

65 We learn the context-sensitive grammar model of SSG from a context-free grammar. [sent-166, score-0.264]

66 Under the learning framework of minimax entropy [25], we enforce the contextual relations by adding statistical constraints sequentially. [sent-167, score-0.393]

67 With more contextual relations being added, the sampled conﬁgurations become more similar to a real scene, and the statistics of the learned distribution become closer to that of target distribution. [sent-171, score-0.393]

68 4 Inference with hierarchical cluster sampling We design a hierarchical cluster sampling algorithm to infer the optimal parse tree for the SSG model. [sent-172, score-0.731]

69 A parse tree speciﬁes a conﬁguration of visual entities. [sent-173, score-0.457]

70 The combination of conﬁgurations makes the solution space expand exponentially, and it is NP-hard to enumerate all parse trees in such a large space. [sent-174, score-0.331]

71 In order to detecting scene components, neither sliding window (top-down) nor binding (bottom-up) approaches can handle the large geometric variations and an enormous number of conﬁgurations. [sent-176, score-0.281]

72 In this paper we combine the bottom-up and top-down process by exploring the contextual relations deﬁned on the grammar model. [sent-177, score-0.684]

73 In the clustering stage, we group visual entities into clusters (tight structures) by ﬁltering the entities based on cooperative “+” relations. [sent-179, score-0.811]

74 (iv), we detect substructures, such as 2D faces, aligned and nested 2D faces, 3D boxes, aligned and stacked 3D boxes (in Fig. [sent-182, score-0.211]

75 The algorithm proposes a new parse tree: pt∗ = pt+Cl∗ with the cluster Cl∗ conditioning on the current parse tree pt. [sent-191, score-0.842]

76 (4) u∈ClAN D ,v∈ptAN D The algorithm gives more weights to the proposals with strong bottom-up support and tight “+” relations by P+ (Cl|I), and simultaneously avoids the exclusive proposals with “-” relations by AN P− D (AG (u)|AG (v)). [sent-193, score-0.658]

77 The marginal probability of each cluster P+ (Cl|I) is computed during the clustering stage, and the probability AN for each pair-wise negative “-” relations P− D (AG (u)|AG (v)) is then calculated and stored in a look-up table. [sent-195, score-0.308]

78 The algorithm also proposes a new parse tree by pruning current parse tree randomly. [sent-196, score-0.818]

79 The UIUC dataset contains 314 cluttered indoor images, of which the ground-truth is two label maps of background layout with/without foreground objects. [sent-200, score-0.408]

80 Our dataset contains 220 images which cover six 6 2D face detection 3D foreground detection 0. [sent-201, score-0.25]

81 8 1 False nagative rate (b) (c) Figure 6: Quantitative performance of 2D face detection (a) and 3D foreground detection (b) in our dataset. [sent-217, score-0.286]

82 indoor scene categories: bedroom, living room, kitchen, classroom, ofﬁce room, and corridor. [sent-219, score-0.313]

83 The ground-truths are hand labeled segments for scene components for each image. [sent-221, score-0.318]

84 7 is obtained by applying different production rules to images in our dataset. [sent-224, score-0.419]

85 With the AND rules only, the algorithm obtains reasonable results and successfully recovers some salient 3D foreground objects and 2D faces. [sent-225, score-0.412]

86 With both the AND and SET rules, the cooperative “+” relations help detect some weak visual entities. [sent-226, score-0.426]

87 Quantitative evaluation: We ﬁrst evaluate the detection of 2D faces, 3D foreground objects in our dataset. [sent-232, score-0.272]

88 6, the red curves show the ROC of 2D faces / 3D objects detection in clustering stage. [sent-235, score-0.297]

89 The blue curves show the ROC of ﬁnal detection given a partial parse tree after MCMC inference. [sent-238, score-0.446]

90 Using the UIUC dataset, we compare our algorithm to four other state-of-the-art indoor scene parsing algorithms, Hoiem et al. [sent-241, score-0.459]

91 By applying the production rules and the contextual relations, our generative grammar model outperforms others as shown in Table. [sent-247, score-0.856]

92 6 Conclusion In this paper, we propose a framework of geometric image parsing using Stochastic Scene Grammar (SSG). [sent-249, score-0.232]

93 The grammar model is used to represent the compositional structure of visual entities. [sent-250, score-0.462]

94 It is beyond the traditional probabilistic context-free grammars (PCFGs) in a few aspects: spatial context, production rules for multiple occurrences of objects, richer image appearance and geometric properties. [sent-251, score-0.58]

95 We also design a hierarchical cluster sampling algorithm that uses contextual relations to accelerate the Markov chain search. [sent-252, score-0.591]

96 The SSG model is ﬂexible to model other compositional structures by applying different production rules and contextual relations. [sent-253, score-0.778]

97 This will be interesting to discover new relations between TV and sofa, desk and chair, bed and night table as demonstrated in [26]. [sent-256, score-0.22]

98 edu/˜ybzhao/research/sceneparsing 7 Figure 7: Experimental results by applying the AND/OR rules (the ﬁrst row) and applying all AND/OR/SET rules (the second row) in our dataset Figure 8: Experimental results of more complex indoor images in UIUC dataset [2]. [sent-261, score-0.475]

99 Segmentation precision Without rules With 3D “-” constraints With AND, OR rules With AND, OR, SET rules [1] 73. [sent-268, score-0.573]

100 (2008) Make3d: Learning 3D scene structure from a single image. [sent-316, score-0.22]

similar papers computed by tfidf model

tfidf for this paper:

wordName wordTfidf (topN-words)

[('parse', 0.331), ('entities', 0.279), ('grammar', 0.264), ('chv', 0.236), ('production', 0.228), ('scene', 0.22), ('relations', 0.22), ('ssg', 0.2), ('rules', 0.191), ('contextual', 0.173), ('faces', 0.173), ('ag', 0.162), ('pt', 0.158), ('foreground', 0.148), ('cooperative', 0.144), ('hinged', 0.127), ('parsing', 0.11), ('compositional', 0.11), ('segments', 0.098), ('indoor', 0.093), ('exclusive', 0.09), ('cluster', 0.088), ('zhu', 0.085), ('layout', 0.083), ('cl', 0.08), ('uiuc', 0.078), ('structures', 0.076), ('boxes', 0.074), ('hedau', 0.073), ('objects', 0.073), ('competitive', 0.069), ('iii', 0.066), ('hoiem', 0.065), ('tree', 0.064), ('ii', 0.063), ('visual', 0.062), ('image', 0.061), ('geometric', 0.061), ('adaptor', 0.055), ('aligned', 0.054), ('rule', 0.052), ('detection', 0.051), ('hebert', 0.05), ('nodes', 0.05), ('hierarchical', 0.049), ('background', 0.049), ('proposals', 0.049), ('porway', 0.048), ('clusters', 0.047), ('box', 0.047), ('los', 0.046), ('discriminative', 0.046), ('angeles', 0.045), ('terminal', 0.045), ('mumford', 0.044), ('switching', 0.043), ('bind', 0.041), ('grammars', 0.039), ('surface', 0.038), ('iv', 0.038), ('stage', 0.037), ('clan', 0.036), ('nagative', 0.036), ('oring', 0.036), ('rset', 0.036), ('et', 0.036), ('stochastic', 0.035), ('cluttered', 0.035), ('line', 0.034), ('relation', 0.034), ('jumps', 0.033), ('types', 0.033), ('gurations', 0.032), ('gurable', 0.032), ('sampling', 0.031), ('tight', 0.03), ('chain', 0.03), ('gupta', 0.03), ('nested', 0.029), ('categories', 0.029), ('room', 0.029), ('competing', 0.029), ('ensemble', 0.029), ('object', 0.028), ('proposes', 0.028), ('energy', 0.028), ('lee', 0.028), ('understanding', 0.028), ('saxena', 0.028), ('kanade', 0.028), ('furniture', 0.028), ('forsyth', 0.028), ('rectangle', 0.028), ('represents', 0.027), ('false', 0.027), ('exploring', 0.027), ('represent', 0.026), ('segmentation', 0.026), ('con', 0.026), ('satisfy', 0.026)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.99999988 127 nips-2011-Image Parsing with Stochastic Scene Grammar

Author: Yibiao Zhao, Song-chun Zhu

2 0.23753421 193 nips-2011-Object Detection with Grammar Models

Author: Ross B. Girshick, Pedro F. Felzenszwalb, David A. McAllester

Abstract: Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difﬁcult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection and show that it outperforms previous high-performance systems on the PASCAL benchmark. Our model represents people using a hierarchy of deformable parts, variable structure and an explicit model of occlusion for partially visible objects. To train the model, we introduce a new discriminative framework for learning structured prediction models from weakly-labeled data. 1

3 0.17928195 1 nips-2011-$\theta$-MRF: Capturing Spatial and Semantic Structure in the Parameters for Scene Understanding

Author: Congcong Li, Ashutosh Saxena, Tsuhan Chen

Abstract: For most scene understanding tasks (such as object detection or depth estimation), the classiﬁers need to consider contextual information in addition to the local features. We can capture such contextual information by taking as input the features/attributes from all the regions in the image. However, this contextual dependence also varies with the spatial location of the region of interest, and we therefore need a different set of parameters for each spatial location. This results in a very large number of parameters. In this work, we model the independence properties between the parameters for each location and for each task, by deﬁning a Markov Random Field (MRF) over the parameters. In particular, two sets of parameters are encouraged to have similar values if they are spatially close or semantically close. Our method is, in principle, complementary to other ways of capturing context such as the ones that use a graphical model over the labels instead. In extensive evaluation over two different settings, of multi-class object detection and of multiple scene understanding tasks (scene categorization, depth estimation, geometric labeling), our method beats the state-of-the-art methods in all the four tasks. 1

4 0.17719904 132 nips-2011-Inferring Interaction Networks using the IBP applied to microRNA Target Prediction

Author: Hai-son P. Le, Ziv Bar-joseph

Abstract: Determining interactions between entities and the overall organization and clustering of nodes in networks is a major challenge when analyzing biological and social network data. Here we extend the Indian Buffet Process (IBP), a nonparametric Bayesian model, to integrate noisy interaction scores with properties of individual entities for inferring interaction networks and clustering nodes within these networks. We present an application of this method to study how microRNAs regulate mRNAs in cells. Analysis of synthetic and real data indicates that the method improves upon prior methods, correctly recovers interactions and clusters, and provides accurate biological predictions. 1

5 0.16305465 247 nips-2011-Semantic Labeling of 3D Point Clouds for Indoor Scenes

Author: Hema S. Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena

Abstract: Inexpensive RGB-D cameras that give an RGB image together with depth data have become widely available. In this paper, we use this data to build 3D point clouds of full indoor scenes such as an ofﬁce and address the task of semantic labeling of these 3D point clouds. We propose a graphical model that captures various features and contextual relations, including the local visual appearance and shape cues, object co-occurence relationships and geometric relationships. With a large number of object classes and relations, the model’s parsimony becomes important and we address that by using multiple types of edge potentials. The model admits efﬁcient approximate inference, and we train it using a maximum-margin learning approach. In our experiments over a total of 52 3D scenes of homes and ofﬁces (composed from about 550 views, having 2495 segments labeled with 27 object classes), we get a performance of 84.06% in labeling 17 object classes for ofﬁces, and 73.38% in labeling 17 object classes for home scenes. Finally, we applied these algorithms successfully on a mobile robot for the task of ﬁnding objects in large cluttered rooms.1 1

6 0.15604213 138 nips-2011-Joint 3D Estimation of Objects and Scene Layout

7 0.10400225 223 nips-2011-Probabilistic Joint Image Segmentation and Labeling

8 0.10225647 46 nips-2011-Better Mini-Batch Algorithms via Accelerated Gradient Methods

9 0.09714897 227 nips-2011-Pylon Model for Semantic Segmentation

10 0.094104648 304 nips-2011-Why The Brain Separates Face Recognition From Object Recognition

11 0.087111302 126 nips-2011-Im2Text: Describing Images Using 1 Million Captioned Photographs

12 0.081008539 154 nips-2011-Learning person-object interactions for action recognition in still images

13 0.074612506 35 nips-2011-An ideal observer model for identifying the reference frame of objects

14 0.072585493 119 nips-2011-Higher-Order Correlation Clustering for Image Segmentation

15 0.072213866 66 nips-2011-Crowdclustering

16 0.071080565 74 nips-2011-Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

17 0.070963323 96 nips-2011-Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition

18 0.070241958 141 nips-2011-Large-Scale Category Structure Aware Image Categorization

19 0.069703244 136 nips-2011-Inverting Grice's Maxims to Learn Rules from Natural Language Extractions

20 0.066345565 61 nips-2011-Contextual Gaussian Process Bandit Optimization

similar papers computed by lsi model

lsi for this paper:

topicId topicWeight

[(0, 0.185), (1, 0.099), (2, -0.117), (3, 0.175), (4, 0.101), (5, -0.011), (6, -0.046), (7, -0.056), (8, 0.064), (9, 0.054), (10, 0.129), (11, -0.029), (12, -0.015), (13, -0.051), (14, -0.049), (15, 0.029), (16, 0.042), (17, -0.047), (18, -0.023), (19, 0.015), (20, 0.002), (21, -0.09), (22, -0.14), (23, 0.066), (24, 0.004), (25, -0.047), (26, 0.03), (27, 0.103), (28, -0.019), (29, 0.027), (30, -0.088), (31, 0.113), (32, -0.115), (33, 0.075), (34, 0.051), (35, -0.0), (36, -0.119), (37, 0.071), (38, -0.074), (39, -0.003), (40, -0.004), (41, -0.076), (42, 0.023), (43, 0.013), (44, -0.07), (45, 0.117), (46, -0.132), (47, 0.035), (48, -0.109), (49, 0.026)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.95419121 127 nips-2011-Image Parsing with Stochastic Scene Grammar

Author: Yibiao Zhao, Song-chun Zhu

2 0.67573768 138 nips-2011-Joint 3D Estimation of Objects and Scene Layout

Author: Andreas Geiger, Christian Wojek, Raquel Urtasun

Abstract: We propose a novel generative model that is able to reason jointly about the 3D scene layout as well as the 3D location and orientation of objects in the scene. In particular, we infer the scene topology, geometry as well as trafﬁc activities from a short video sequence acquired with a single camera mounted on a moving car. Our generative model takes advantage of dynamic information in the form of vehicle tracklets as well as static information coming from semantic labels and geometry (i.e., vanishing points). Experiments show that our approach outperforms a discriminative baseline based on multiple kernel learning (MKL) which has access to the same image information. Furthermore, as we reason about objects in 3D, we are able to signiﬁcantly increase the performance of state-of-the-art object detectors in their ability to estimate object orientation. 1

3 0.66788328 193 nips-2011-Object Detection with Grammar Models

Author: Ross B. Girshick, Pedro F. Felzenszwalb, David A. McAllester

4 0.64934611 247 nips-2011-Semantic Labeling of 3D Point Clouds for Indoor Scenes

Author: Hema S. Koppula, Abhishek Anand, Thorsten Joachims, Ashutosh Saxena

5 0.5977484 1 nips-2011-$\theta$-MRF: Capturing Spatial and Semantic Structure in the Parameters for Scene Understanding

Author: Congcong Li, Ashutosh Saxena, Tsuhan Chen

6 0.5974502 132 nips-2011-Inferring Interaction Networks using the IBP applied to microRNA Target Prediction

7 0.54912746 154 nips-2011-Learning person-object interactions for action recognition in still images

8 0.47880819 290 nips-2011-Transfer Learning by Borrowing Examples for Multiclass Object Detection

9 0.46983281 35 nips-2011-An ideal observer model for identifying the reference frame of objects

10 0.46834275 304 nips-2011-Why The Brain Separates Face Recognition From Object Recognition

11 0.45083863 223 nips-2011-Probabilistic Joint Image Segmentation and Labeling

12 0.44215071 293 nips-2011-Understanding the Intrinsic Memorability of Images

13 0.43693763 166 nips-2011-Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object Model Learning

14 0.42991239 266 nips-2011-Spatial distance dependent Chinese restaurant processes for image segmentation

15 0.42693982 126 nips-2011-Im2Text: Describing Images Using 1 Million Captioned Photographs

16 0.39991805 233 nips-2011-Rapid Deformable Object Detection using Dual-Tree Branch-and-Bound

17 0.37489867 285 nips-2011-The Kernel Beta Process

18 0.37455097 130 nips-2011-Inductive reasoning about chimeric creatures

19 0.37191948 136 nips-2011-Inverting Grice's Maxims to Learn Rules from Natural Language Extractions

20 0.37159598 173 nips-2011-Modelling Genetic Variations using Fragmentation-Coagulation Processes

similar papers computed by lda model

lda for this paper:

topicId topicWeight

[(0, 0.013), (4, 0.163), (20, 0.058), (26, 0.03), (31, 0.056), (33, 0.057), (43, 0.044), (45, 0.082), (57, 0.038), (60, 0.047), (61, 0.184), (65, 0.013), (74, 0.046), (83, 0.032), (84, 0.011), (99, 0.045)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.85517055 127 nips-2011-Image Parsing with Stochastic Scene Grammar

Author: Yibiao Zhao, Song-chun Zhu

2 0.74177855 193 nips-2011-Object Detection with Grammar Models

Author: Ross B. Girshick, Pedro F. Felzenszwalb, David A. McAllester

3 0.72424847 130 nips-2011-Inductive reasoning about chimeric creatures

Author: Charles Kemp

Abstract: Given one feature of a novel animal, humans readily make inferences about other features of the animal. For example, winged creatures often ﬂy, and creatures that eat ﬁsh often live in the water. We explore the knowledge that supports these inferences and compare two approaches. The ﬁrst approach proposes that humans rely on abstract representations of dependency relationships between features, and is formalized here as a graphical model. The second approach proposes that humans rely on speciﬁc knowledge of previously encountered animals, and is formalized here as a family of exemplar models. We evaluate these models using a task where participants reason about chimeras, or animals with pairs of features that have not previously been observed to co-occur. The results support the hypothesis that humans rely on explicit representations of relationships between features. Suppose that an eighteenth-century naturalist learns about a new kind of animal that has fur and a duck’s bill. Even though the naturalist has never encountered an animal with this pair of features, he should be able to make predictions about other features of the animal—for example, the animal could well live in water but probably does not have feathers. Although the platypus exists in reality, from a eighteenth-century perspective it qualiﬁes as a chimera, or an animal that combines two or more features that have not previously been observed to co-occur. Here we describe a probabilistic account of inductive reasoning and use it to account for human inferences about chimeras. The inductive problems we consider are special cases of the more general problem in Figure 1a where a reasoner is given a partially observed matrix of animals by features then asked to infer the values of the missing entries. This general problem has been previously studied and is addressed by computational models of property induction, categorization, and generalization [1–7]. A challenge faced by all of these models is to capture the background knowledge that guides inductive inferences. Some accounts rely on similarity relationships between animals [6, 8], others rely on causal relationships between features [9, 10], and others incorporate relationships between animals and relationships between features [11]. We will evaluate graphical models that capture both kinds of relationships (Figure 1a), but will focus in particular on relationships between features. Psychologists have previously suggested that humans rely on explicit mental representations of relationships between features [12–16]. Often these representations are described as theories—for example, theories that specify a causal relationship between having wings and ﬂying, or living in the sea and eating ﬁsh. Relationships between features may take several forms: for example, one feature may cause, enable, prevent, be inconsistent with, or be a special case of another feature. For simplicity, we will treat all of these relationships as instances of dependency relationships between features, and will capture them using an undirected graphical model. Previous studies have used graphical models to account for human inferences about features but typically these studies consider toy problems involving a handful of novel features such as “has gene X14” or “has enzyme Y132” [9, 11]. Participants might be told, for example, that gene X14 leads to the production of enzyme Y132, then asked to use this information when reasoning about novel animals. Here we explore whether a graphical model approach can account for inferences 1 (a) slow heavy flies (b) wings hippo 1 1 0 0 rhino 1 1 0 0 sparrow 0 0 1 1 robin 0 0 1 1 new ? ? 1 ? o Figure 1: Inductive reasoning about animals and features. (a) Inferences about the features of a new animal onew that ﬂies may draw on similarity relationships between animals (the new animal is similar to sparrows and robins but not hippos and rhinos), and on dependency relationships between features (ﬂying and having wings are linked). (b) A graph product produced by combining the two graph structures in (a). about familiar features. Working with familiar features raises a methodological challenge since participants have a substantial amount of knowledge about these features and can reason about them in multiple ways. Suppose, for example, that you learn that a novel animal can ﬂy (Figure 1a). To conclude that the animal probably has wings, you might consult a mental representation similar to the graph at the top of Figure 1a that speciﬁes a dependency relationship between ﬂying and having wings. On the other hand, you might reach the same conclusion by thinking about ﬂying creatures that you have previously encountered (e.g. sparrows and robins) and noticing that these creatures have wings. Since the same conclusion can be reached in two different ways, judgments about arguments of this kind provide little evidence about the mental representations involved. The challenge of working with familiar features directly motivates our focus on chimeras. Inferences about chimeras draw on rich background knowledge but require the reasoner to go beyond past experience in a fundamental way. For example, if you learn that an animal ﬂies and has no legs, you cannot make predictions about the animal by thinking of ﬂying, no-legged creatures that you have previously encountered. You may, however, still be able to infer that the novel animal has wings if you understand the relationship between ﬂying and having wings. We propose that graphical models over features can help to explain how humans make inferences of this kind, and evaluate our approach by comparing it to a family of exemplar models. The next section introduces these models, and we then describe two experiments designed to distinguish between the models. 1 Reasoning about objects and features Our models make use of a binary matrix D where the rows {o1 , . . . , o129 } correspond to objects, and the columns {f 1 , . . . , f 56 } correspond to features. A subset of the objects is shown in Figure 2a, and the full set of features is shown in Figure 2b and its caption. Matrix D was extracted from the Leuven natural concept database [17], which includes 129 animals and 757 features in total. We chose a subset of these features that includes a mix of perceptual and behavioral features, and that includes many pairs of features that depend on each other. For example, animals that “live in water” typically “can swim,” and animals that have “no legs” cannot “jump far.” Matrix D can be used to formulate problems where a reasoner observes one or two features of a new object (i.e. animal o130 ) and must make inferences about the remaining features of the animal. The next two sections describe graphical models that can be used to address this problem. The ﬁrst graphical model O captures relationships between objects, and the second model F captures relationships between features. We then discuss how these models can be combined, and introduce a family of exemplar-style models that will be compared with our graphical models. A graphical model over objects Many accounts of inductive reasoning focus on similarity relationships between objects [6, 8]. Here we describe a tree-structured graphical model O that captures these relationships. The tree was constructed from matrix D using average linkage clustering and the Jaccard similarity measure, and part of the resulting structure is shown in Figure 2a. The subtree in Figure 2a includes clusters 2 alligator caiman crocodile monitor lizard dinosaur blindworm boa cobra python snake viper chameleon iguana gecko lizard salamander frog toad tortoise turtle anchovy herring sardine cod sole salmon trout carp pike stickleback eel flatfish ray plaice piranha sperm whale squid swordfish goldfish dolphin orca whale shark bat fox wolf beaver hedgehog hamster squirrel mouse rabbit bison elephant hippopotamus rhinoceros lion tiger polar bear deer dromedary llama giraffe zebra kangaroo monkey cat dog cow horse donkey pig sheep (a) (b) can swim lives in water eats fish eats nuts eats grain eats grass has gills can jump far has two legs has no legs has six legs has four legs can fly can be ridden has sharp teeth nocturnal has wings strong predator can see in dark eats berries lives in the sea lives in the desert crawls lives in the woods has mane lives in trees can climb well lives underground has feathers has scales slow has fur heavy Figure 2: Graph structures used to deﬁne graphical models O and F. (a) A tree that captures similarity relationships between animals. The full tree includes 129 animals, and only part of the tree is shown here. The grey points along the branches indicate locations where a novel animal o130 could be attached to the tree. (b) A network capturing pairwise dependency relationships between features. The edges capture both positive and negative dependencies. All edges in the network are shown, and the network also includes 20 isolated nodes for the following features: is black, is blue, is green, is grey, is pink, is red, is white, is yellow, is a pet, has a beak, stings, stinks, has a long neck, has feelers, sucks blood, lays eggs, makes a web, has a hump, has a trunk, and is cold-blooded. corresponding to amphibians and reptiles, aquatic creatures, and land mammals, and the subtree omitted for space includes clusters for insects and birds. We assume that the features in matrix D (i.e. the columns) are generated independently over O: P (f i |O, π i , λi ). P (D|O, π, λ) = i i i i The distribution P (f |O, π , λ ) is based on the intuition that nearby nodes in O tend to have the same value of f i . Previous researchers [8, 18] have used a directed graphical model where the distribution at the root node is based on the baserate π i , and any other node v with parent u has the following conditional probability distribution: i P (v = 1|u) = π i + (1 − π i )e−λ l , if u = 1 i π i − π i e−λ l , if u = 0 (1) where l is the length of the branch joining node u to node v. The variability parameter λi captures the extent to which feature f i is expected to vary over the tree. Note, for example, that any node v must take the same value as its parent u when λ = 0. To avoid free parameters, the feature baserates π i and variability parameters λi are set to their maximum likelihood values given the observed values of the features {f i } in the data matrix D. The conditional distributions in Equation 1 induce a joint distribution over all of the nodes in graph O, and the distribution P (f i |O, π i , λi ) is computed by marginalizing out the values of the internal nodes. Although we described O as a directed graphical model, the model can be converted into an equivalent undirected model with a potential for each edge in the tree and a potential for the root node. Here we use the undirected version of the model, which is a natural counterpart to the undirected model F described in the next section. The full version of structure O in Figure 2a includes 129 familiar animals, and our task requires inferences about a novel animal o130 that must be slotted into the structure. Let D′ be an expanded version of D that includes a row for o130 , and let O′ be an expanded version of O that includes a node for o130 . The edges in Figure 2a are marked with evenly spaced gray points, and we use a 3 uniform prior P (O′ ) over all trees that can be created by attaching o130 to one of these points. Some of these trees have identical topologies, since some edges in Figure 2a have multiple gray points. Predictions about o130 can be computed using: P (D′ |D) = P (D′ |O′ , D)P (O′ |D) ∝ O′ P (D′ |O′ , D)P (D|O′ )P (O′ ). (2) O′ Equation 2 captures the basic intuition that the distribution of features for o130 is expected to be consistent with the distribution observed for previous animals. For example, if o130 is known to ﬂy then the trees with high posterior probability P (O′ |D) will be those where o130 is near other ﬂying creatures (Figure 1a), and since these creatures have wings Equation 2 predicts that o130 probably also has wings. As this example suggests, model O captures dependency relationships between features implicitly, and therefore stands in contrast to models like F that rely on explicit representations of relationships between features. A graphical model over features Model F is an undirected graphical model deﬁned over features. The graph shown in Figure 2b was created by identifying pairs where one feature depends directly on another. The author and a research assistant both independently identiﬁed candidate sets of pairwise dependencies, and Figure 2b was created by merging these sets and reaching agreement about how to handle any discrepancies. As previous researchers have suggested [13, 15], feature dependencies can capture several kinds of relationships. For example, wings enable ﬂying, living in the sea leads to eating ﬁsh, and having no legs rules out jumping far. We work with an undirected graph because some pairs of features depend on each other but there is no clear direction of causal inﬂuence. For example, there is clearly a dependency relationship between being nocturnal and seeing in the dark, but no obvious sense in which one of these features causes the other. We assume that the rows of the object-feature matrix D are generated independently from an undirected graphical model F deﬁned over the feature structure in Figure 2b: P (oi |F). P (D|F) = i Model F includes potential functions for each node and for each edge in the graph. These potentials were learned from matrix D using the UGM toolbox for undirected graphical models [19]. The learned potentials capture both positive and negative relationships: for example, animals that live in the sea tend to eat ﬁsh, and tend not to eat berries. Some pairs of feature values never occur together in matrix D (there are no creatures that ﬂy but do not have wings). We therefore chose to compute maximum a posteriori values of the potential functions rather than maximum likelihood values, and used a diffuse Gaussian prior with a variance of 100 on the entries in each potential. After learning the potentials for model F, we can make predictions about a new object o130 using the distribution P (o130 |F). For example, if o130 is known to ﬂy (Figure 1a), model F predicts that o130 probably has wings because the learned potentials capture a positive dependency between ﬂying and having wings. Combining object and feature relationships There are two simple ways to combine models O and F in order to develop an approach that incorporates both relationships between features and relationships between objects. The output combination model computes the predictions of both models in isolation, then combines these predictions using a weighted sum. The resulting model is similar to a mixture-of-experts model, and to avoid free parameters we use a mixing weight of 0.5. The structure combination model combines the graph structures used by the two models and relies on a set of potentials deﬁned over the resulting graph product. An example of a graph product is shown in Figure 1b, and the potential functions for this graph are inherited from the component models in the natural way. Kemp et al. [11] use a similar approach to combine a functional causal model with an object model O, but note that our structure combination model uses an undirected model F rather than a functional causal model over features. Both combination models capture the intuition that inductive inferences rely on relationships between features and relationships between objects. The output combination model has the virtue of 4 simplicity, and the structure combination model is appealing because it relies on a single integrated representation that captures both relationships between features and relationships between objects. To preview our results, our data suggest that the combination models perform better overall than either O or F in isolation, and that both combination models perform about equally well. Exemplar models We will compare the family of graphical models already described with a family of exemplar models. The key difference between these model families is that the exemplar models do not rely on explicit representations of relationships between objects and relationships between features. Comparing the model families can therefore help to establish whether human inferences rely on representations of this sort. Consider ﬁrst a problem where a reasoner must predict whether object o130 has feature k after observing that it has feature i. An exemplar model addresses the problem by retrieving all previouslyobserved objects with feature i and computing the proportion that have feature k: P (ok = 1|oi = 1) = |f k & f i | |f i | (3) where |f k | is the number of objects in matrix D that have feature k, and |f k & f i | is the number that have both feature k and feature i. Note that we have streamlined our notation by using ok instead of o130 to refer to the kth feature value for object o130 . k Suppose now that the reasoner observes that object o130 has features i and j. The natural generalization of Equation 3 is: P (ok = 1|oi = 1, oj = 1) = |f k & f i & f j | |f i & f j | (4) Because we focus on chimeras, |f i & f j | = 0 and Equation 4 is not well deﬁned. We therefore evaluate an exemplar model that computes predictions for the two observed features separately then computes the weighted sum of these predictions: P (ok = 1|oi = 1, oj = 1) = wi |f k & f i | |f k & f j | + wj . i| |f |f j | (5) where the weights wi and wj must sum to one. We consider four ways in which the weights could be set. The ﬁrst strategy sets wi = wj = 0.5. The second strategy sets wi ∝ |f i |, and is consistent with an approach where the reasoner retrieves all exemplars in D that are most similar to the novel animal and reports the proportion of these exemplars that have feature k. The third strategy sets wi ∝ |f1i | , and captures the idea that features should be weighted by their distinctiveness [20]. The ﬁnal strategy sets weights according to the coherence of each feature [21]. A feature is coherent if objects with that feature tend to resemble each other overall, and we deﬁne the coherence of feature i as the expected Jaccard similarity between two randomly chosen objects from matrix D that both have feature i. Note that the ﬁnal three strategies are all consistent with previous proposals from the psychological literature, and each one might be expected to perform well. Because exemplar models and prototype models are often compared, it is natural to consider a prototype model [22] as an additional baseline. A standard prototype model would partition the 129 animals into categories and would use summary statistics for these categories to make predictions about the novel animal o130 . We will not evaluate this model because it corresponds to a coarser version of model O, which organizes the animals into a hierarchy of categories. The key characteristic shared by both models is that they explicitly capture relationships between objects but not features. 2 Experiment 1: Chimeras Our ﬁrst experiment explores how people make inferences about chimeras, or novel animals with features that have not previously been observed to co-occur. Inferences about chimeras raise challenges for exemplar models, and therefore help to establish whether humans rely on explicit representations of relationships between features. Each argument can be represented as f i , f j → f k 5 exemplar r = 0.42 7 feature F exemplar (wi = |f i |) (wi = 0.5) r = 0.44 7 object O r = 0.69 7 output combination r = 0.31 7 structure combination r = 0.59 7 r = 0.60 7 5 5 5 5 5 3 3 3 3 3 3 all 5 1 1 0 1 r = 0.06 7 conflict 0.5 1 1 0 0.5 1 r = 0.71 7 1 0 0.5 1 r = −0.02 7 1 0 0.5 1 r = 0.49 7 0 5 5 5 5 3 3 3 3 1 5 3 0.5 r = 0.57 7 5 3 1 0 0.5 1 r = 0.51 7 edge 0.5 r = 0.17 7 1 1 0 0.5 1 r = 0.64 7 1 0 0.5 1 r = 0.83 7 1 0 0.5 1 r = 0.45 7 1 0 0.5 1 r = 0.76 7 0 5 5 5 5 3 3 3 3 1 5 3 0.5 r = 0.79 7 5 3 1 1 0 0.5 1 r = 0.26 7 other 1 0 1 0 0.5 1 r = 0.25 7 1 0 0.5 1 r = 0.19 7 1 0 0.5 1 r = 0.25 7 1 0 0.5 1 r = 0.24 7 0 7 5 5 5 5 5 3 3 3 3 1 5 3 0.5 r = 0.33 3 1 1 0 0.5 1 1 0 0.5 1 1 0 0.5 1 1 0 0.5 1 1 0 0.5 1 0 0.5 1 Figure 3: Argument ratings for Experiment 1 plotted against the predictions of six models. The y-axis in each panel shows human ratings on a seven point scale, and the x-axis shows probabilities according to one of the models. Correlation coefﬁcients are shown for each plot. where f i and f k are the premises (e.g. “has no legs” and “can ﬂy”) and f k is the conclusion (e.g. “has wings”). We are especially interested in conﬂict cases where the premises f i and f j lead to opposite conclusions when taken individually: for example, most animals with no legs do not have wings, but most animals that ﬂy do have wings. Our models that incorporate feature structure F can resolve this conﬂict since F includes a dependency between “wings” and “can ﬂy” but not between “wings” and “has no legs.” Our models that do not include F cannot resolve the conﬂict and predict that humans will be uncertain about whether the novel animal has wings. Materials. The object-feature matrix D includes 447 feature pairs {f i , f j } such that none of the 129 animals has both f i and f j . We selected 40 pairs (see the supporting material) and created 400 arguments in total by choosing 10 conclusion features for each pair. The arguments can be assigned to three categories. Conﬂict cases are arguments f i , f j → f k such that the single-premise arguments f i → f k and f j → f k lead to incompatible predictions. For our purposes, two singlepremise arguments with the same conclusion are deemed incompatible if one leads to a probability greater than 0.9 according to Equation 3, and the other leads to a probability less than 0.1. Edge cases are arguments f i , f j → f k such that the feature network in Figure 2b includes an edge between f k and either f i or f j . Note that some arguments are both conﬂict cases and edge cases. All arguments that do not fall into either one of these categories will be referred to as other cases. The 400 arguments for the experiment include 154 conﬂict cases, 153 edge cases, and 120 other cases. 34 arguments are both conﬂict cases and edge cases. We chose these arguments based on three criteria. First, we avoided premise pairs that did not co-occur in matrix D but that co-occur in familiar animals that do not belong to D. For example, “is pink” and “has wings” do not co-occur in D but “ﬂamingo” is a familiar animal that has both features. Second, we avoided premise pairs that speciﬁed two different numbers of legs—for example, {“has four legs,” “has six legs”}. Finally, we aimed to include roughly equal numbers of conﬂict cases, edge cases, and other cases. Method. 16 undergraduates participated for course credit. The experiment was carried out using a custom-built computer interface, and one argument was presented on screen at a time. Participants 6 rated the probability of the conclusion on seven point scale where the endpoints were labeled “very unlikely” and “very likely.” The ten arguments for each pair of premises were presented in a block, but the order of these blocks and the order of the arguments within these blocks were randomized across participants. Results. Figure 3 shows average human judgments plotted against the predictions of six models. The plots in the ﬁrst row include all 400 arguments in the experiment, and the remaining rows show results for conﬂict cases, edge cases, and other cases. The previous section described four exemplar models, and the two shown in Figure 3 are the best performers overall. Even though the graphical models include more numerical parameters than the exemplar models, recall that these parameters are learned from matrix D rather than ﬁt to the experimental data. Matrix D also serves as the basis for the exemplar models, which means that all of the models can be compared on equal terms. The ﬁrst row of Figure 3 suggests that the three models which include feature structure F perform better than the alternatives. The output combination model is the worst of the three models that incorporate F, and the correlation achieved by this model is signiﬁcantly greater than the correlation achieved by the best exemplar model (p < 0.001, using the Fisher transformation to convert correlation coefﬁcients to z scores). Our data therefore suggest that explicit representations of relationships between features are needed to account for inductive inferences about chimeras. The model that includes the feature structure F alone performs better than the two models that combine F with the object structure O, which may not be surprising since Experiment 1 focuses speciﬁcally on novel animals that do not slot naturally into structure O. Rows two through four suggest that the conﬂict arguments in particular raise challenges for the models which do not include feature structure F. Since these conﬂict cases are arguments f i , f j → f k where f i → f k has strength greater than 0.9 and f j → f k has strength less than 0.1, the ﬁrst exemplar model averages these strengths and assigns an overall strength of around 0.5 to each argument. The second exemplar model is better able to differentiate between the conﬂict arguments, but still performs substantially worse than the three models that include structure F. The exemplar models perform better on the edge arguments, but are outperformed by the models that include F. Finally, all models achieve roughly the same level of performance on the other arguments. Although the feature model F performs best overall, the predictions of this model still leave room for improvement. The two most obvious outliers in the third plot in the top row represent the arguments {is blue, lives in desert → lives in woods} and {is pink, lives in desert → lives in woods}. Our participants sensibly infer that any animal which lives in the desert cannot simultaneously live in the woods. In contrast, the Leuven database indicates that eight of the twelve animals that live in the desert also live in the woods, and the edge in Figure 2b between “lives in the desert” and “lives in the woods” therefore represents a positive dependency relationship according to model F. This discrepancy between model and participants reﬂects the fact that participants made inferences about individual animals but the Leuven database is based on features of animal categories. Note, for example, that any individual animal is unlikely to live in the desert and the woods, but that some animal categories (including snakes, salamanders, and lizards) are found in both environments. 3 Experiment 2: Single-premise arguments Our results so far suggest that inferences about chimeras rely on explicit representations of relationships between features but provide no evidence that relationships between objects are important. It would be a mistake, however, to conclude that relationships between objects play no role in inductive reasoning. Previous studies have used object structures like the example in Figure 2a to account for inferences about novel features [11]—for example, given that alligators have enzyme Y132 in their blood, it seems likely that crocodiles also have this enzyme. Inferences about novel objects can also draw on relationships between objects rather than relationships between features. For example, given that a novel animal has a beak you will probably predict that it has feathers, not because there is any direct dependency between these two features, but because the beaked animals that you know tend to have feathers. Our second experiment explores inferences of this kind. Materials and Method. 32 undergraduates participated for course credit. The task was identical to Experiment 1 with the following exceptions. Each two-premise argument f i , f j → f k from Experiment 1 was converted into two one-premise arguments f i → f k and f j → f k , and these 7 feature F exemplar r = 0.78 7 object O r = 0.54 7 output combination r = 0.75 7 structure combination r = 0.75 7 all 5 5 5 5 5 3 3 3 3 3 1 1 0 edge 0.5 1 r = 0.87 7 1 0 0.5 1 r = 0.87 7 1 0 0.5 1 r = 0.84 7 1 0 0.5 1 r = 0.86 7 0 5 5 5 3 3 3 1 5 3 0.5 r = 0.85 7 5 3 1 1 0 0.5 1 r = 0.79 7 other r = 0.77 7 1 0 0.5 1 r = 0.21 7 1 0 0.5 1 r = 0.74 7 1 0 0.5 1 r = 0.66 7 0 5 5 5 5 3 3 3 3 1 r = 0.73 7 5 0.5 3 1 1 0 0.5 1 1 0 0.5 1 1 0 0.5 1 1 0 0.5 1 0 0.5 1 Figure 4: Argument ratings and model predictions for Experiment 2. one-premise arguments were randomly assigned to two sets. 16 participants rated the 400 arguments in the ﬁrst set, and the other 16 rated the 400 arguments in the second set. Results. Figure 4 shows average human ratings for the 800 arguments plotted against the predictions of ﬁve models. Unlike Figure 3, Figure 4 includes a single exemplar model since there is no need to consider different feature weightings in this case. Unlike Experiment 1, the feature model F performs worse than the other alternatives (p < 0.001 in all cases). Not surprisingly, this model performs relatively well for edge cases f j → f k where f j and f k are linked in Figure 2b, but the ﬁnal row shows that the model performs poorly across the remaining set of arguments. Taken together, Experiments 1 and 2 suggest that relationships between objects and relationships between features are both needed to account for human inferences. Experiment 1 rules out an exemplar approach but models that combine graph structures over objects and features perform relatively well in both experiments. We considered two methods for combining these structures and both performed equally well. Combining the knowledge captured by these structures appears to be important, and future studies can explore in detail how humans achieve this combination. 4 Conclusion This paper proposed that graphical models are useful for capturing knowledge about animals and their features and showed that a graphical model over features can account for human inferences about chimeras. A family of exemplar models and a graphical model deﬁned over objects were unable to account for our data, which suggests that humans rely on mental representations that explicitly capture dependency relationships between features. Psychologists have previously used graphical models to capture relationships between features, but our work is the ﬁrst to focus on chimeras and to explore models deﬁned over a large set of familiar features. Although a simple undirected model accounted relatively well for our data, this model is only a starting point. The model incorporates dependency relationships between features, but people know about many speciﬁc kinds of dependencies, including cases where one feature causes, enables, prevents, or is inconsistent with another. An undirected graph with only one class of edges cannot capture this knowledge in full, and richer representations will ultimately be needed in order to provide a more complete account of human reasoning. Acknowledgments I thank Madeleine Clute for assisting with this research. This work was supported in part by the Pittsburgh Life Sciences Greenhouse Opportunity Fund and by NSF grant CDI-0835797. 8 References [1] R. N. Shepard. Towards a universal law of generalization for psychological science. Science, 237:1317– 1323, 1987. [2] J. R. Anderson. The adaptive nature of human categorization. Psychological Review, 98(3):409–429, 1991. [3] E. Heit. A Bayesian analysis of some forms of inductive reasoning. In M. Oaksford and N. Chater, editors, Rational models of cognition, pages 248–274. Oxford University Press, Oxford, 1998. [4] J. B. Tenenbaum and T. L. Grifﬁths. Generalization, similarity, and Bayesian inference. Behavioral and Brain Sciences, 24:629–641, 2001. [5] C. Kemp and J. B. Tenenbaum. Structured statistical models of inductive reasoning. Psychological Review, 116(1):20–58, 2009. [6] D. N. Osherson, E. E. Smith, O. Wilkie, A. Lopez, and E. Shaﬁr. Category-based induction. Psychological Review, 97(2):185–200, 1990. [7] D. J. Navarro. Learning the context of a category. In J. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R.S. Zemel, and A. Culotta, editors, Advances in Neural Information Processing Systems 23, pages 1795–1803. 2010. [8] C. Kemp, T. L. Grifﬁths, S. Stromsten, and J. B. Tenenbaum. Semi-supervised learning with trees. In Advances in Neural Information Processing Systems 16, pages 257–264. MIT Press, Cambridge, MA, 2004. [9] B. Rehder. A causal-model theory of conceptual representation and categorization. Journal of Experimental Psychology: Learning, Memory, and Cognition, 29:1141–1159, 2003. [10] B. Rehder and R. Burnett. Feature inference and the causal structure of categories. Cognitive Psychology, 50:264–314, 2005. [11] C. Kemp, P. Shafto, and J. B. Tenenbaum. An integrated account of generalization across objects and features. Cognitive Psychology, in press. [12] S. E. Barrett, H. Abdi, G. L. Murphy, and J. McCarthy Gallagher. Theory-based correlations and their role in children’s concepts. Child Development, 64:1595–1616, 1993. [13] S. A. Sloman, B. C. Love, and W. Ahn. Feature centrality and conceptual coherence. Cognitive Science, 22(2):189–228, 1998. [14] D. Yarlett and M. Ramscar. A quantitative model of counterfactual reasoning. In T. G. Dietterich, S. Becker, and Z. Ghahramani, editors, Advances in Neural Information Processing Systems 14, pages 123–130. MIT Press, Cambridge, MA, 2002. [15] W. Ahn, J. K. Marsh, C. C. Luhmann, and K. Lee. Effect of theory-based feature correlations on typicality judgments. Memory and Cognition, 30(1):107–118, 2002. [16] D. C. Meehan C. McNorgan, R. A. Kotack and K. McRae. Feature-feature causal relations and statistical co-occurrences in object concepts. Memory and Cognition, 35(3):418–431, 2007. [17] S. De Deyne, S. Verheyen, E. Ameel, W. Vanpaemel, M. J. Dry, W. Voorspoels, and G. Storms. Exemplar by feature applicability matrices and other Dutch normative data for semantic concepts. Behavior Research Methods, 40(4):1030–1048, 2008. [18] J. P. Huelsenbeck and F. Ronquist. MRBAYES: Bayesian inference of phylogenetic trees. Bioinformatics, 17(8):754–755, 2001. [19] M. Schmidt. UGM: A Matlab toolbox for probabilistic undirected graphical models. 2007. Available at http://people.cs.ubc.ca/∼schmidtm/Software/UGM.html. [20] L. J. Nelson and D. T. Miller. The distinctiveness effect in social categorization: you are what makes you unusual. Psychological Science, 6:246–249, 1995. [21] A. L. Patalano, S. Chin-Parker, and B. H. Ross. The importance of being coherent: category coherence, cross-classiﬁcation and reasoning. Journal of memory and language, 54:407–424, 2006. [22] S. K. Reed. Pattern recognition and categorization. Cognitive Psychology, 3:393–407, 1972. 9

4 0.72087264 213 nips-2011-Phase transition in the family of p-resistances

Author: Morteza Alamgir, Ulrike V. Luxburg

Abstract: We study the family of p-resistances on graphs for p 1. This family generalizes the standard resistance distance. We prove that for any ﬁxed graph, for p = 1 the p-resistance coincides with the shortest path distance, for p = 2 it coincides with the standard resistance distance, and for p ! 1 it converges to the inverse of the minimal s-t-cut in the graph. Secondly, we consider the special case of random geometric graphs (such as k-nearest neighbor graphs) when the number n of vertices in the graph tends to inﬁnity. We prove that an interesting phase transition takes place. There exist two critical thresholds p⇤ and p⇤⇤ such that if p < p⇤ , then the p-resistance depends on meaningful global properties of the graph, whereas if p > p⇤⇤ , it only depends on trivial local quantities and does not convey any useful information. We can explicitly compute the critical values: p⇤ = 1 + 1/(d 1) and p⇤⇤ = 1 + 1/(d 2) where d is the dimension of the underlying space (we believe that the fact that there is a small gap between p⇤ and p⇤⇤ is an artifact of our proofs). We also relate our ﬁndings to Laplacian regularization and suggest to use q-Laplacians as regularizers, where q satisﬁes 1/p⇤ + 1/q = 1. 1

5 0.70409042 39 nips-2011-Approximating Semidefinite Programs in Sublinear Time

Author: Dan Garber, Elad Hazan

Abstract: In recent years semideﬁnite optimization has become a tool of major importance in various optimization and machine learning problems. In many of these problems the amount of data in practice is so large that there is a constant need for faster algorithms. In this work we present the ﬁrst sublinear time approximation algorithm for semideﬁnite programs which we believe may be useful for such problems in which the size of data may cause even linear time algorithms to have prohibitive running times in practice. We present the algorithm and its analysis alongside with some theoretical lower bounds and an improved algorithm for the special problem of supervised learning of a distance metric. 1

6 0.69987321 139 nips-2011-Kernel Bayes' Rule

7 0.69391251 279 nips-2011-Target Neighbor Consistent Feature Weighting for Nearest Neighbor Classification

8 0.65551734 97 nips-2011-Finite Time Analysis of Stratified Sampling for Monte Carlo

9 0.64595467 154 nips-2011-Learning person-object interactions for action recognition in still images

10 0.63896704 64 nips-2011-Convergent Bounds on the Euclidean Distance

11 0.63751781 247 nips-2011-Semantic Labeling of 3D Point Clouds for Indoor Scenes

12 0.63343894 166 nips-2011-Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object Model Learning

13 0.62909192 168 nips-2011-Maximum Margin Multi-Instance Learning

14 0.62460142 303 nips-2011-Video Annotation and Tracking with Active Learning

15 0.62176752 242 nips-2011-See the Tree Through the Lines: The Shazoo Algorithm

16 0.62062699 138 nips-2011-Joint 3D Estimation of Objects and Scene Layout

17 0.6183328 223 nips-2011-Probabilistic Joint Image Segmentation and Labeling

18 0.61565214 231 nips-2011-Randomized Algorithms for Comparison-based Search

19 0.61441851 204 nips-2011-Online Learning: Stochastic, Constrained, and Smoothed Adversaries

20 0.61432827 103 nips-2011-Generalization Bounds and Consistency for Latent Structural Probit and Ramp Loss