Matrix completion for weakly-supervised multi-label image classification

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 37, Issue 1, 2015, Pages 121-135

  Cabral, Ricardo ^a,b   De La Torre, Fernando ^c   Costeira, João Paulo ^b   Bernardino, Alexandre ^b  

^a CARNEGIE MELLON UNIVERSITY   (United States)

^b INSTITUTO SUPERIOR TÉCNICO   (Portugal)

^c CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

Multi label image classification; Nuclear norm; Rank minimization; Segmentation; Weakly supervised learning

Indexed keywords

CLASSIFICATION (OF INFORMATION); IMAGE SEGMENTATION; LEARNING SYSTEMS; MATRIX ALGEBRA; OBJECT RECOGNITION; SEMANTICS;

EXPERIMENTAL VALIDATIONS; LOW-RANK MATRIX COMPLETIONS; MULTI-LABEL; MULTIPLE-INSTANCE LEARNING; NUCLEAR NORM; RANK MINIMIZATIONS; SUPERVISED IMAGE CLASSIFICATIONS; WEAKLY-SUPERVISED LEARNING;

IMAGE CLASSIFICATION;

EID: 84916877392     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2014.2343234     Document Type: Article

References (62)

1. H. Wang, C. Ding, and H. Huang, "Multi-label linear discriminant analysis," in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 126-139.
2. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, "The Pascal visual object classes (VOC) challenge," Int. J. Comput. Vis., vol. 88, no. 2, pp. 303-338, 2010.
3. B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman, "LabelMe: A database and web-based tool for image annotation," Int. J. Comput. Vis., vol. 77, no. 1-3, pp. 157-173, 2008.
4. M. H. Nguyen, L. Torresani, F. De la Torre, and C. Rother, "Weakly supervised discriminative localization and classification: A joint learning process," in Proc. Int. Conf. Comput. Vis., 2009, pp. 1925-1932.
5. B. Russell, W. Freeman, A. Efros, J. Sivic, and A. Zisserman, "Using multiple segmentations to discover objects and their extent in image collections," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2006, pp. 1605-1614.
6. R. Fergus, P. Perona, and A. Zisserman, "Object class recognition by unsupervised scale-invariant learning," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2003, pp. 264-271.
7. M. Jamieson, A. Fazly, S. Dickinson, S. Stevenson, and S. Wachsmuth, "Learning structured appearance models from captioned images of cluttered scenes," in Proc. IEEE 11th Int. Conf. Comput. Vis., 2007, pp. 1-8.
8. C. Yang, M. Dong, and J. Hua, "Region-based image annotation using asymmetrical support vector machine-based multiple-instance learning," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2006, pp. 2057-2063.
9. Z.-H. Zhou and M. Zhang, "Multi-instance multi-label learning with application to scene classification," in Proc. Neural Inf. Process. Syst., 2006, pp. 1609-1616.
10. Z.-J. Zha, X.-S. Hua, T. Mei, J. Wang, and G.-J. Q. Zengfu, "Joint multi-label multi-instance learning for image classification," in Proc. IEEE Comput. Vis. Pattern Recog., 2008, pp. 1-8.
11. S. Vijayanarasimhan and K. Grauman, "What's it going to cost you?: Predicting effort versus informativeness for multi-label image annotations," in Proc. IEEE Comput. Vis. Pattern Recog., 2009, pp. 2262-2269.
12. P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan, "Object detection with discriminatively trained part-based models," IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627-1645, Sep. 2010.
13. F. Li and C. Sminchisescu, "Convex multiple instance learning by estimating likelihood ratio," in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 1360-1368.
14. J. Sivic and A. Zisserman, "Video Google: A text retrieval approach to object matching in videos," in Proc. IEEE 9th Int. Conf. Comput. Vis. Pattern Recog., 2003, pp. 1470-1477.
15. E. Candes and B. Recht, "Exact low-rank matrix completion via convex optimization," in Proc. 46th Annu. Allerton Conf. Commun., Control, Comput., 2008, pp. 806-812.
16. S. Ma, D. Goldfarb, and L. Chen, "Fixed point and bregman iterative methods for matrix rank minimization," Math. Program., vol. 128, no. 1-2, pp. 321-353, 2011.
17. R. S. Cabral, F. De la Torre, J. P. Costeira, and A. Bernardino, "Matrix completion for multi-label image classification," in Proc. Adv. Neural Inf. Process. Syst., 2011, pp. 190-198.
18. K. Barnard and D. Forsyth, "Learning the semantics of words and pictures," in Proc. IEEE 8th Int. Conf. Comput. Vis., 2001, pp. 408-415.
19. C. Desai, D. Ramanan, and C. Fowlkes, "Discriminative models for multi-class object layout," in Proc. IEEE 12th Int. Conf. Comput. Vis., 2009, pp. 229-236.
20. S. Petridis, W. Liu, and J. Pessiot, "Localizing objects while learning their appearance," in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 452-466.
21. M. Blaschko and C. Lampert, "Learning to localize objects with structured output regression," in Proc. 10th Eur. Conf. Comput. Vis., 2008, pp. 2-15.
22. J. Tighe and S. Lazebnik, "Superparsing: Scalable nonparametric image parsing with superpixels," in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 352-365.
23. T. G. Dietterich, R. H. Lathrop, and T. Lozano-Perez, "Solving the multiple instance problem with axis-parallel rectangles," Artif. Intell., vol. 89, no. 1, pp. 31-71, 1997.
24. O. Maron and A. Ratan, "Multiple-instance learning for natural scene classification," in Proc. 15th Int. Conf. Mach. Learn., 1998, pp. 341-349.
25. A. Vezhnevets and J. Buhmann, "Towards weakly supervised semantic segmentation by means of multiple instance and multi-task learning," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 3249-3256.
26. O. Yakhnenko and V. Honavar, "Multi-instance multi-label learning for image classification with large vocabularies," in Proc. Brit. Mach. Vis. Conf., 2011, pp. 1-12.
27. T. L. Berg, A. C. Berg, J. Edwards, and D. A. Forsyth, "Who's in the picture?" in Proc. Adv. Neural Inf. Process. Syst., 2004, pp. 137-144.
28. M. Fazel, H. Hindi, and S. P. Boyd, "A rank minimization heuristic with application to minimum order system approximation," in Proc. Amer. Conf. Control, 2001, pp. 4734-4739.
29. F. Xiong, O. I. Camps, and M. Sznaier, "Dynamic context for tracking behind occlusions," in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 580-593.
30. E. J. Candès, J. K. Romberg, and T. Tao, "Stable signal recovery from incomplete and inaccurate measurements," Commun. Pure Appl. Math., vol. 59, no. 8, pp. 1207-1223, 2006.
31. Z. Lin, M. Chen, L. Wu, and Y. Ma, "The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices," Tech. Rep. UILU-ENG-09-2215, submitted to Mathematical Programming, Oct. 2009.
32. J.-F. Cai, E. J. Candes, and Z. Shen, "A singular value thresholding algorithm for matrix completion," SIAM J. Optim., vol. 20, no. 4, pp. 1956-1982, 2008.
33. K.-C. Toh and S. Yun, "An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems," Pacific J. Optim., vol. 6, pp. 615-640, 2010.
34. R. H. Keshavan, A. Montanari, and S. Oh, "Matrix completion from a few entries," IEEE Trans. Inf. Theory, vol. 56, no. 6, pp. 2980-2998, Jun. 2010.
35. L. Balzano, R. Nowak, and B. Recht, "Online identification and tracking of subspaces from highly incomplete information," in Proc. Allerton Conf. Commun., Control, Comput., 2010, pp. 704-711.
36. R. S. Cabral, J. P. Costeira, F. De la Torre, and A. Bernardino, "Fast incremental method for matrix completion: An application to trajectory correction," in Proc. IEEE 18th Int. Conf. Image Process., 2011, pp. 1417-1420.
37. Y. Dai, H. Li, and M. He, "Element-wise factorization for N-view projective reconstruction," in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 396-409.
38. J. Wright, A. Ganesh, S. Rao, and Y. Ma, "Robust principal component analysis: Exact recovery of corrupted low-rank matrices by convex optimization," in Proc. Adv. Neural Inf. Process. Syst., 2009, pp. 2080-2088.
39. P. Favaro, R. Vidal, and A. Ravichandran, "A closed form solution to robust subspace estimation and clustering," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 1801-1807.
40. B. Cheng, G. Liu, J. Wang, Z. Huang, and S. Yan, "Multi-task low-rank affinity pursuit for image segmentation," in Proc. IEEE Int. Conf. Comput. Vis., 2011, pp. 2439-2446.
41. G. Zhu and S. Yan, "Image tag refinement towards low-rank, content-tag prior and error sparsity," in Proc. Int. Conf. Multimedia, 2010, pp. 461-470.
42. Z. Zhang, Y. Matsushita, and Y. Ma, "Camera calibration with lens distortion from low-rank textures," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 2321-2328.
43. H. Pirsiavash, D. Ramanan, and C. Fowlkes, "Bilinear classifiers for visual recognition," in Proc. Adv. Neural Inf. Process. Syst., 2009, pp. 1482-1490.
44. N. Loeff and A. Farhadi, "Scene discovery by matrix factorization," in Proc. 10th Eur. Conf. Comput. Vis., 2008, pp. 451-464.
45. X. Tan, Y. Li, J. Liu, and L. Jiang, "Face liveness detection from a single image with sparse low rank bilinear discriminative model," in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 504-517.
46. A. B. Goldberg, X. Zhu, B. Recht, J. ming Xu, and R. Nowak, "Transduction with matrix completion: Three birds with one stone," in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 757-765.
47. Z. Harchaoui, M. Douze, M. Paulin, M. Dudik, and J. Malick, "Large-scale image classification with trace-norm regularization," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 3386-3393.
48. A. Bosch, A. Zisserman, and X. Munoz, "Scene classification via pLSA," in Proc. 9th Eur. Conf. Comput. Vis., 2006, pp. 517-530.
49. D. Huang, R. Cabral, and F. De la Torre, "Robust regression," in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 616-630.
50. J. Duchi, S. Shalev-Shwartz, Y. Singer, and T. Chandra, "Efficient projections onto the l1-ball for learning in high dimensions," in Proc. 25th Int. Conf. Mach. Learn., 2008, pp. 272-279.
51. C. Liu, J. Yuen, and A. Torralba, "Nonparametric scene parsing via label transfer," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 12, pp. 2368-2382, Dec. 2011.
52. J. Xiao, J. Hays, K. A. Ehinger, A. Oliva, and A. Torralba, "SUN database: Large-scale scene recognition from abbey to zoo," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 3485-3492.
53. J. Shotton, J. M. Winn, C. Rother, and A. Criminisi, "Textonboost: Joint appearance, shape and context modeling for multi-class object recognition and segmentation," in Proc. 9th Eur. Conf. Comput. Vis., 2006, pp. 1-15.
54. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2005, pp. 886-893.
55. T. Mitchell, Machine Learning. New York, NY, USA: McGraw-Hill, 1997.
56. D. G. Lowe, "Distinctive image features from scale-invariant keypoints," Int. J. Comput. Vis., vol. 60, no. 2, pp. 91-110, 2004.
57. A. Vedaldi and B. Fulkerson. (2008). VLFeat: An open and portable library of computer vision algorithms [Online]. Available: http://www.vlfeat.org/
58. P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun, "OverFeat: Integrated recognition, localization and detection using convolutional networks," in Proc. Int. Conf. Learning Representations, 2014.
59. A. Razavian, H. Azizpour, J. Sullivan, and S. Carlsson, "CNN features off-the-shelf: An astounding baseline for recognition," in CVPR, 2014.
60. P. Arbelaez, M. Maire, C. Fowlkes, and J. Malik, "Contour detection and hierarchical image segmentation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 5, pp. 898-916, May 2011.
61. S. Vijayanarasimhan and K. Grauman, "Efficient region search for object detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 1401-1408.
62. J.-B. Hiriart-Urruty and C. Lemaréchal, Fundamentals of Convex Analysis. Berlin, Germany: Springer-Verlag, 2001.