Unsupervised object class discovery via saliency-guided multiple class learning

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 37, Issue 4, 2015, Pages 862-875

  Zhu, Jun Yan ^a   Wu, Jiajun ^b   Xu, Yan ^c   Chang, Eric ^d   Tu, Zhuowen ^e  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b TSINGHUA UNIVERSITY   (China)

^c BEIHANG UNIVERSITY   (China)

^d MICROSOFT RESEARCH ASIA   (China)

^e UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

multiple instance learning; object detection; saliency; Unsupervised object discovery; weakly supervised learning

Indexed keywords

COMPUTER VISION; LEARNING SYSTEMS; OBJECT RECOGNITION; SUPERVISED LEARNING; UNSUPERVISED LEARNING;

HIGH-LEVEL VISIONS; INTEGRATED FRAMEWORKS; MULTIPLE INSTANCE LEARNING; OBJECT LOCALIZATION; SALIENCY; SALIENCY DETECTION; UNSUPERVISED OBJECT DISCOVERIES; WEAKLY SUPERVISED LEARNING;

OBJECT DETECTION;

EID: 84924750243     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2014.2353617     Document Type: Article

References (61)

1. B. Alexe, T. Deselaers, and V. Ferrari, "Measuring the objectness of image windows, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 11, pp. 2189-2202, Nov. 2012.
2. S. Andrews, I. Tsochantaridis, and T. Hofmann, "Support vector machines for multiple-instance learning, " in Proc. Neural Inf. Process. Syst., 2002, pp. 561-568.
3. B. Babenko, P. Doll-ar, Z. Tu, and S. Belongie, "Simultaneous learning and alignment: Multi-instance and multi-pose learning, " in Proc. Workshop Faces in Real-Life Images, Eur. Conf. Comput. Vis., 2008.
4. B. Babenko, M.-H. Yang, and S. Belongie, "Robust object tracking with online multiple instance learning, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no, 8, pp. 1619-1632, Aug. 2011.
5. D. Batra, A. Kowdle, D. Parikh, J. Luo, and T. Chen, "iCoseg: Interactive co-segmentation with intelligent scribble guidance, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2010, pp. 3169-3176.
6. J. Carreira and C. Sminchisescu, "Constrained parametric mincuts for automatic object segmentation, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2010, pp. 3241-3248.
7. K. Chang, T. Liu, and S. Lai, "From co-saliency to cosegmentation: An efficient and fully unsupervised energy minimization model, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2011, pp. 2129-2136.
8. M.-M. Cheng, G.-X. Zhang, N. J. Mitra, X. Huang, and S.-M. Hu, "Global contrast based salient region detection, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2011, pp. 409-416.
9. O. Chum and A. Zisserman, "An exemplar model for learning object classes, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2007, pp. 1-8.
10. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm, " J. Royal Statist. Soc. Ser. B, vol. 39, no. 1, pp. 1-38, 1977.
11. T. Deselaers, B. Alexe, and V. Ferrari, "Weakly supervised localization and learning with generic knowledge, " Int. J. Comput. Vis., vol. 100, no. 3, pp. 275-293, 2012.
12. T. G. Dietterich, R. H. Lathrop, and T. Lozano-P-erez, "Solving the multiple instance problem with axis-parallel rectangles, " Artif. Intell., vol. 89, no. 1/2, pp. 31-71, 1997.
13. C. Doersch, A. Gupta, and A. A. Efros, "Mid-level visual element discovery as discriminative mode seeking, " in Proc. Neural Inf. Process. Syst., 2013, pp. 494-502.
14. P. Doll-ar, B. Babenko, S. Belongie, P. Perona, and Z. Tu, "Multiple component learning for object detection, " in Proc. Eur. Conf. Comput. Vis., 2008, pp. 211-224.
15. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY, USA: Wiley-Interscience, Nov. 2001.
16. I. Endres and D. Hoiem, "Category independent object proposals, " in Proc. Eur. Conf. Comput. Vis., 2010, pp. 575-588.
17. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL visual object classes challenge 2007 (VOC2007) results [Online]. Available: http://www.pascalnetwork. org/challenges/VOC/voc2007/workshop/index.html, 2007.
18. M. Everingham, A. Zisserman, C. K. I. Williams, and L. Van Gool. The PASCAL visual object classes challenge 2006 (VOC2006) results [Online]. Available: http://www.pascal-network.org/challenges/VOC/voc2006/results.pdf, 2006.
19. L. Fei-Fei, R. Fergus, S. Member, and P. Perona, "One-shot learning of object categories, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 4, pp. 594-611, Apr. 2006.
20. P. F. Felzenszwalb, R. B. Girshick, and D. R. David A. McAllester, "Object detection with discriminatively trained part-based models, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 32, no. 9, pp. 1627-1645, Sep. 2010.
21. J. Feng, Y. Wei, L. Tao, C. Zhang, and J. Sun, "Salient object detection by composition, " in Proc. Int. Conf. Comput. Vis., 2011, pp. 1028-1035.
22. Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting, " J. Comput. Syst. Sci., vol. 55, no. 1, pp. 119-139, 1997.
23. B. J. Frey and N. Jojic, "Transformation-invariant clustering using the em algorithm, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 1, pp. 1-17, Jan. 2003.
24. G. Heitz and D. Koller, "Learning spatial context: Using stuff to find things, " in Proc. Eur. Conf. Comput. Vis., 2008, pp. 30-43.
25. X. Hou and L. Zhang, "Saliency detection: A spectral residual approach, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2007, pp. 1-8.
26. A. Joulin, F. Bach, and J. Ponce, "Multi-class cosegmentation, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2012, pp. 542-549.
27. G. Kim, C. Faloutsos, and M. Hebert, "Unsupervised modeling of object categories using link analysis techniques, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2008, pp. 1-8.
28. G. Kim and E. P. Xing, "On multiple foreground cosegmentation, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2012, pp. 837-844.
29. F. D. la Torre and M. J. Black, "A framework for robust subspace learning, " Int. J. Comput. Vis., vol. 54, no. 1, pp. 117-142, 2003.
30. Y. J. Lee and K. Grauman, "Shape discovery from unlabeled image collections, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2009, pp. 2254-2261.
31. Y. J. Lee and K. Grauman, "Object-graphs for context-aware category discovery, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2010, pp. 1-8.
32. Y. J. Lee and K. Grauman, "Learning the easy things first: Selfpaced visual category discovery, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2011, pp. 1721-1728.
33. C. Leistner, A. Saffari, and H. Bischof, "Miforests: Multipleinstance learning with randomized trees, " in Proc. Eur. Conf. Comput. Vis., 2010, pp. 29-42.
34. Q. Li, J. Wu, and Z. Tu, "Harvesting mid-level visual concepts from large-scale internet images, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2013, pp. 851-858.
35. N. Loeff and A. Farhadi, "Scene discovery by matrix factorization, " in Proc. Eur. Conf. Comput. Vis., 2008, pp. 451-464.
36. L. Mason, J. Baxter, P. Bartlett, and M. Frean, "Boosting algorithms as gradient descent, " in Proc. Neural Inf. Process. Syst., 2000, pp. 512-518.
37. F. Moosmann, D. Larlus, and F. Jurie, "Learning saliency maps for object categorization, " in Proc. ECCV Workshop Representation Use Prior Knowl. Vis., 2006.
38. L. Mukherjee, V. Singh, J. Xu, and M. D. Collins, "Analyzing the subspace structure of related images: Concurrent segmentation of image sets, " in Proc. Eur. Conf. Comput. Vis., 2012, pp. 128-142.
39. A. Oliva and A. Torralba, "Modeling the shape of the scene: A holistic representation of the spatial envelope, " Int. J. Comput. Vis., vol. 42, no. 3, pp. 145-175, 2001.
40. M. Pandey and S. Lazebnik, "Scene recognition and weakly supervised object localization with deformable part-based models, " in Proc. Int. Conf. Comput. Vis., 2011, pp. 1307-1314.
41. R. Rahmani, S. A. Goldman, H. Zhang, J. Krettek, and J. E. Fritts, "Localized content based image retrieval, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 30, no. 11, pp. 1902-1912, Nov. 2008.
42. C. Rother, T. Minka, and A. Blake, "Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2006, pp. 993-1000.
43. B. C. Russell, A. A. Efros, J. Sivic, W. T. Freeman, and A. Zisserman, "Using multiple segmentations to discover objects and their extent in image collections, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2006, pp. 1605-1614.
44. U. Rutishauser, D. Walther, C. Koch, and P. Perona, "Is bottom-up attention useful for object recognition?" in Proc. Conf. Comput. Vis. Pattern Recognit., 2004, pp. II-37-II-44.
45. J. Salojarvi, K. Puolamaki, and S. Kaski, "Expectation maximization algorithms for conditional likelihoods, " in Proc. Neural Inf. Process. Syst., 2005, pp. 752-759.
46. S. Savarese and L. Fei-Fei, "3D generic object categorization, localization and pose estimation, " in Proc. Int. Conf. Comput. Vis., 2007, pp. 1-8.
47. J. Shotton, A. W. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, "Real-time human pose recognition in parts from single depth images, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2011, pp. 1297-1304.
48. A. Strehl and J. Ghosh, "Cluster ensembles-A knowledge reuse framework for combining multiple partitions, " J. Mach. Learn. Res., vol. 3, no. 3, pp. 583-617, 2003.
49. M. Stricker and M. Orengo, "Similarity of color images, " in Proc. Storage Retrieval Image Video Databases, 1995, pp. 381-392.
50. T. Tuytelaars, C. H. Lampert, M. B. Blaschko, and W. Buntine, "Unsupervised object discovery: A comparison, " Int. J. Comput. Vis., vol. 88, no. 2, pp. 284-302, 2009.
51. S. Vicente, C. Rother, and V. Kolmogorov, "Object cosegmentation, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2011, pp. 2217-2224.
52. S. Vijayanarasimhan and K. Grauman, "Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization, " in Proc. Conf. Comput. Vis. Pattern Recognit., 2008, pp. 1-8.
53. P. A. Viola and M. J. Jones, "Robust real-time face detection, " Int. J. Comput. Vis., vol. 57, no. 2, pp. 137-154, 2004.
54. P. A. Viola, J. C. Platt, and C. Zhang, "Multiple instance boosting for object detection, " in Proc. Neural Inf. Process. Syst., 2006, pp. 1417-1426.
55. L. Xu, J.Neufeld, B. Larson, and D. Schuurmans, "Maximummargin clustering, " in Proc. Neural Inf. Process. Syst., 2005, pp. 1537-1544.
56. D. Zhang, F. Wang, L. Si, and T. Li, "M3IC: Maximum margin multiple instance clustering, " in Proc. Int. Joint Conf. Artif. Intell., 2009, pp. 1339-1344.
57. D. Zhang, F. Wang, L. Si, and T. Li, "Maximum margin multiple instance clustering with its applications to image and text clustering, " IEEE Trans. Neural Netw., vol. 22, no. 5, pp. 739-751, May 2011.
58. M.-L. Zhang and Z.-H. Zhou, "Multi-instance clustering with applications to multi-instance prediction, " Appl. Intell., vol. 31, pp. 47-68, Aug. 2009.
59. B. Zhao, F. Wang, and C. Zhang, "Efficient multiclass maximum margin clustering, " in Proc. Int. Conf. Mach. Learn., 2008, pp. 1248-1255.
60. Z.-H. Zhou, M.-L. Zhang, S.-J. Huang, and Y.-F. Li, "Multiinstance multi-label learning, " Artif. Intell., vol. 176, no. 1, pp. 2291-2320, 2012.
61. L. Zhu, Y. Chen, and A. L. Yuille, "Unsupervised learning of probabilistic grammar-Markov models for object categories, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 10, pp. 114-128, Jan. 2009.