iccv iccv2013 iccv2013-390 iccv2013-390-reference knowledge-graph by maker-knowledge-mining

390 iccv-2013-Shufflets: Shared Mid-level Parts for Fast Object Detection


Source: pdf

Author: Iasonas Kokkinos

Abstract: We present a method to identify and exploit structures that are shared across different object categories, by using sparse coding to learn a shared basis for the ‘part’ and ‘root’ templates of Deformable Part Models (DPMs). Our first contribution consists in using Shift-Invariant Sparse Coding (SISC) to learn mid-level elements that can translate during coding. This results in systematically better approximations than those attained using standard sparse coding. To emphasize that the learned mid-level structures are shiftable we call them shufflets. Our second contribution consists in using the resulting score to construct probabilistic upper bounds to the exact template scores, instead of taking them ‘at face value ’ as is common in current works. We integrate shufflets in DualTree Branch-and-Bound and cascade-DPMs and demonstrate that we can achieve a substantial acceleration, with practically no loss in performance.


reference text

[1] http://vision.mas.ecp.fr/Personnel/iasonas/dpms.html. 2, 7

[2] Y. Aytar and A. Zisserman. Tabula rasa: Model transfer for object category detection. In ICCV, 2011. 3, 8

[3] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 1

[4] T. Dean, M. Ruzon, M. Segal, J. Shlens, S. Vijayanarasimhan, and J. Yagnik. Fast, accurate detection of

[5]

[6]

[7]

[8]

[9]

[10]

[11]

[12]

[13]

[14]

[15]

[16] 100,000 object classes on a single machine. In CVPR, 2013. 2, 8 S. Dickinson, A. Pentland, and A. Rozenfeld. 3-d shape recovery using distributed aspect matching. PAMI, 1992. 2 C. Dubout and F. Fleuret. Exact acceleration of linear object detectors. In ECCV, 2012. 1, 2 G. Ettinger. Large hierarchical object recognition using libraries of parameterized sub-parts. In CVPR, 1988. 2 P. Felzenszwalb, R. Girshick, and D. McAllester. Cascade object detection with deformable part models. In CVPR, 2010. 1, 2, 6, 7, 8 P. Felzenszwalb and D. Huttenlocher. Pictorial Structures for Object Recognition. IJCV, 2005. 1 S. Fidler and A. Leonardis. Towards Scalable Representations of Object Categories:Learning a Hierarchy of Parts. In CVPR, 2007. 3 R. Girshick, P. Felzenszwalb, and D. McAllester. Discriminatively trained deformable part models, release 5. http://people.cs.uchicago.edu/ rbg/latent-release5/. 2, 7 R. Girshick, H. O. Song, and T. Darrell. Discriminatively activated sparselets. In ICML, 2013. 1, 3, 8 R. Grosse, R. Raina, H. Kwong, and A. Ng. Shift-invariant sparse coding for audio classification. In UAI, 2007. 4 D. Jacobs. Groper: A grouping based object recognition system for two-dimensional objects. In IEEE Workshop on Computer Vision, 1987. 2 K. Kavukcuoglu, P. Sermanet, Y.-L. Boureau, K. Gregor, M. Mathieu, and Y. LeCun. Learning convolutional feature hierarchies for visual recognition. In NIPS, 2010. 3, 8 I. Kokkinos. Rapid deformable object detection using dualtree branch-and-bound. In NIPS, 2011. 1, 2, 6, 7

[17] I. Kokkinos. Bounding Part Scores for Rapid Detection with Deformable Part Models. In 2nd Parts and Attributes Workshop, ECCV, 2012. 1, 2, 4, 6

[18] I. Kokkinos and A. Yuille. Inference and Learning with Hierarchical Shape Models. IJCV, 2011. 4, 8

[19] A. Krizhevsky, I. Sutskever, and G. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. In NIPS, 2012. 3, 8

[20] H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In ICML, 2009. 3, 8

[21] B. Leibe, A. Leonardis, and B. Schiele. Combined Object Categorization and Segmentation with an Implicit Shape Model. In ECCV, 2004. SLCV workshop. 2

[22] J. Mairal, F. Bach, J. Ponce, and G. Sapiro. Online dictionary learning for sparse coding. In ICML, 2009. 3

[23] K. Mikolajczyk, B. Leibe, and B. Schiele. Multiple object class detection with a generative model. In CVPR, 2006. 2

[24] M. Mitzenmacher and E. Upfal. Probability and computing - randomized algorithms and probabilistic analysis. Cambridge University Press, 2005. 5

[25] A. Opelt, A. Pinz, and A. Zisserman. Boundary-fragmentmodel for object detection. In CVPR, 2006. 2

[26] P. Ott and M. Everingham. Shared parts for deformable partbased models. In CVPR, 2011. 3

[27] H. Pirsiavash and D. Ramanan. Steerable part models. In CVPR, 2012. 1, 2, 3, 8

[28] N. Razavi, J. Gall, and L. V. Gool. Scalable multi-class object detection. In CVPR, 2011. 2, 3

[29] H. O. Song, S. Zickler, T. Althoff, R. B. Girshick, M. Fritz, C. Geyer, P. F. Felzenszwalb, and T. Darrell. Sparselet mod-

[30] [3 1]

[32]

[33]

[34]

[35]

[36]

[37] els for efficient multiclass object detection. In ECCV, 2012. 1, 2, 3, 4, 5 A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, B. Schiele, and L. V. Gool. Towards multi-view object class detection. In CVPR, 2006. 2 S. Todorovic and N. Ahuja. Learning subcategory relevances for category recognition. In CVPR, 2008. 3 A. Torralba, K. P. Murphy, and W. T. Freeman. Sharing Visual Features for Multiclass and Multiview Object Detection. In CVPR, 2004. 2 A. Vedaldi and A. Zisserman. Sparse Kernel Approximations for Efficient Classification and Detection. In CVPR, 2012. 1, 2 Y. J. Xi Song, Tianfu Wu and S.-C. Zhu. Discriminatively trained and-or tree models for object detection. In CVPR, 2013. 8 M. D. Zeiler, G. W. Taylor, and R. Fergus. Adaptive deconvolutional networks for mid and high level feature learning. In ICCV, 2011. 3, 8 L. Zhu, Y. Chen, A. Torralba, W. T. Freeman, and A. L. Yuille. Part and appearance sharing: Recursive compositional models. In CVPR, 2010. 3 S. C. Zhu and A. Yuille. FORMS: A Flexible Object Recognition and Modeling System. IJCV, 20(3), 1996. 2 1400