nips nips2011 nips2011-168 nips2011-168-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Hua Wang, Heng Huang, Farhad Kamangar, Feiping Nie, Chris H. Ding
Abstract: Multi-instance learning (MIL) considers input as bags of instances, in which labels are assigned to the bags. MIL is useful in many real-world applications. For example, in image categorization semantic meanings (labels) of an image mostly arise from its regions (instances) instead of the entire image (bag). Existing MIL methods typically build their models using the Bag-to-Bag (B2B) distance, which are often computationally expensive and may not truly reflect the semantic similarities. To tackle this, in this paper we approach MIL problems from a new perspective using the Class-to-Bag (C2B) distance, which directly assesses the relationships between the classes and the bags. Taking into account the two major challenges in MIL, high heterogeneity on data and weak label association, we propose a novel Maximum Margin Multi-Instance Learning (M3 I) approach to parameterize the C2B distance by introducing the class specific distance metrics and the locally adaptive significance coefficients. We apply our new approach to the automatic image categorization tasks on three (one single-label and two multilabel) benchmark data sets. Extensive experiments have demonstrated promising results that validate the proposed method.
[1] O. Maron and A.L. Ratan. Multiple-instance learning for natural scene classification. In ICML, 1998.
[2] Y. Chen and J.Z. Wang. Image categorization by learning and reasoning with regions. JMLR, 5:913–939, 2004.
[3] Z.H. Zhou and M.L. Zhang. Multi-instance multi-label learning with application to scene classification. In NIPS, 2007.
[4] Z.J. Zha, X.S. Hua, T. Mei, J. Wang, G.J. Qi, and Z. Wang. Joint multi-label multi-instance learning for image classification. In CVPR, 2008.
[5] R. Jin, S. Wang, and Z.H. Zhou. Learning a distance metric from multi-instance multi-label data. In CVPR, 2009.
[6] M. Guillaumin, J. Verbeek, and C. Schmid. Multiple instance metric learning from automatically labeled bags of faces. In ECCV, 2010.
[7] H. Wang, F. Nie, and H. Huang. Learning instance specific distance for multi-instance classification. In AAAI, 2011.
[8] H. Wang, F. Nie, H. Huang, and Y. Yang. Learning frame relevance for video classification. In ACM MM, 2011.
[9] O. Boiman, E. Shechtman, and M. Irani. In defense of nearest-neighbor based image classification. In CVPR, 2008.
[10] A.W.M. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain. Content-based image retrieval at the end of the early years. IEEE TPAMI, 22(12):1349–1380, 2002.
[11] H. Wang, H. Huang, and C. Ding. Image annotation using multi-label correlated Green’s function. In ICCV, 2009.
[12] H. Wang, H. Huang, and C. Ding. Multi-label feature transform for image classifications. In ECCV, 2010.
[13] H. Wang, C. Ding, and H. Huang. Multi-label linear discriminant analysis. In ECCV, pages 126–139. Springer, 2010.
[14] H. Wang, H. Huang, and C. Ding. Image annotation using bi-relational graph of images and semantic labels. In CVPR, 2011.
[15] M. Schultz and T. Joachims. Learning a distance metric from relative comparisons. In NIPS, 2003.
[16] A. Frome, Y. Singer, and J. Malik. Image retrieval and classification using local distance functions. In NIPS, 2007.
[17] A. Frome, Y. Singer, F. Sha, and J. Malik. Learning globally-consistent local distance functions for shape-based image retrieval and classification. In ICCV, 2007.
[18] Z. Wang, Y. Hu, and L.T. Chia. Image-to-Class Distance Metric Learning for Image Classification. In ECCV, 2010.
[19] P. Duygulu, K. Barnard, J. De Freitas, and D. Forsyth. Object recognition as machine translation: Learning a lexicon for a fixed image vocabulary. In ECCV, 2002.
[20] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2010 (VOC2010) Results. http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/.
[21] H. Wang, C. Ding, and H. Huang. Multi-label classification: Inconsistency and class balanced k-nearest neighbor. In AAAI, 2010.
[22] J. Wang and J.D. Zucker. Solving the multiple-instance problem: A lazy learning approach. In ICML, 2000.
[23] R.E. Schapire and Y. Singer. BoosTexter: A boosting-based system for text categorization. Machine learning, 39(2):135–168, 2000. 9