Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence

Volumn 39, Issue 1, 2017, Pages 189-203

  Cinbis, Ramazan Gokberk ^a   Verbeek, Jakob ^b   Schmid, Cordelia ^b  

^a BILKENT UNIVERSITY   (Turkey)

^b UNIV GRENOBLE ALPES   (France)

Author keywords

object detection; Weakly supervised learning

Indexed keywords

COMPUTER VISION; ITERATIVE METHODS; LEARNING SYSTEMS; LOCATION; LOCKS (FASTENERS); NEURAL NETWORKS; OBJECT DETECTION; SUPERVISED LEARNING;

CONVOLUTIONAL NEURAL NETWORK; EXPERIMENTAL EVALUATION; LOCALIZATION ACCURACY; MULTIPLE INSTANCE LEARNING; OBJECT LOCALIZATION; REFINEMENT METHODS; SUPERVISED TRAININGS; WEAKLY SUPERVISED LEARNING;

OBJECT RECOGNITION;

EID: 85003782026     PISSN: 01628828     EISSN: None     Source Type: Journal    
DOI: 10.1109/TPAMI.2016.2535231     Document Type: Article

References (56)

1. B. Alexe, T. Deselaers, V. Ferrari, "What is an object" in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2010, pp. 73-80.
2. B. Alexe, T. Deselaers, V. Ferrari, "Measuring the objectnessof image windows, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 34, no. 11, pp. 2189-2202, Nov. 2012.
3. F. Alted, "Why modern CPUs are starving, what can be doneabout it, " Comput. Sci. Eng., vol. 12, no. 2, pp. 68-71, 2010.
4. S. Bagon, O. Brostovski, M. Galun, M. Irani, "Detecting andsketching the common, " in Proc. IEEE Conf. Comput. Vis. PatternRecog., 2010, pp. 33-40.
5. Y. Bengio, J. Louradour, R. Collobert, J. Weston, "Curriculumlearning, " in Proc. 28th Annu. Int. Conf. Mach. Learn., 2009, pp. 41-48.
6. T. Berg, A. Berg, J. Edwards, M. Maire, R. White, Y. Teh, E. Learned-Miller, D. Forsyth, "Names, faces in the news, "in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2004, pp. 848-854.
7. H. Bilen, V. Namboodiri, L. Van Gool, "Object, action classificationwith latent window parameters, " Int. J. Comput. Vis., vol. 106, no. 3, pp. 237-251, 2014.
8. H. Bilen, M. Pedersoli, T. Tuytelaars, "Weakly supervisedobject detection with posterior regularization, " in Proc. Brit. Mach. Vis. Conf., 2014.
9. M. Blaschko, A. Vedaldi, A. Zisserman, "Simultaneous objectdetection, ranking with weak supervision, " in Proc. Adv. NeuralInf. Process. Syst., 2010, pp. 235-243.
10. D. Blei, A. Ng, M. Jordan, "Latent Dirichlet allocation, " J. Mach. Learn., vol. 3, pp. 993-1022, 2003.
11. M. Cho, S. Kwak, C. Schmid, J. Ponce, "Unsupervised objectdiscovery, localization in the wild: Part-based matching withbottom-up region proposals, " in Proc. IEEE Conf. Comput. Vis. PatternRecog., 2015, pp. 1201-1210.
12. O. Chum, A. Zisserman, "An exemplar model for learningobject classes, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2007, pp. 1-8.
13. R. Cinbis, J. Verbeek, C. Schmid, "Segmentation driven objectdetection with Fisher vectors, " in Proc. Int. Conf. Comput. Vis., 2013, pp. 2968-2975.
14. R. Cinbis, J. Verbeek, C. Schmid, "Multi-fold MIL training forweakly supervised object localization, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 2409-2416.
15. D. Crandall, D. Huttenlocher, "Weakly supervised learning ofpart-based spatial models for visual object recognition, " in Proc. 9th Eur. Conf. Comput. Vis., 2006, pp. 16-29.
16. G. Csurka, C. Dance, L. Fan, J. Willamowski, C. Bray, "Visualcategorization with bags of keypoints, " in Proc. ECCV Int. WorkshopStatist. Learn. Comput. Vis., 2004.
17. T. Deselaers, B. Alexe, V. Ferrari, "Weakly supervised localizationand learning with generic knowledge, " Int. J. Comput. Vis., vol. 100, no. 3, pp. 257-293, 2012.
18. T. Dietterich, R. Lathrop, T. Lozano-Perez, "Solving the multipleinstance problem with axis-parallel rectangles, " Artif. Intell., vol. 89, no. 1-2, pp. 31-71, 1997.
19. M. Everingham, J. Sivic, A. Zisserman, "Taking the bite out ofautomatic naming of characters in TV video, " Image Vis. Comput., vol. 27, no. 5, pp. 545-559, 2009.
20. M. Everingham, L. van Gool, C. Williams, J. Winn, A. Zisserman, "The PASCAL visual object classes (VOC) challenge, " Int. J. Comput. Vis., vol. 88, no. 2, pp. 303-338, 2010.
21. P. Felzenszwalb, R. Grishick, D. McAllester, 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.
22. R. Girshick, J. Donahue, T. Darrell, J. Malik, "Rich feature hierarchiesfor accurate object detection, semantic segmentation, "in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, pp. 580-587.
23. R. Girshick, P. Felzenszwalb, D. McAllester. (2012). Discriminativelytrained deformable part models, release acty [Online]. Available: http://people. cs. uchicago. edu/rbg/latent-release5.
24. C. Gu, P. Arbelaez, Y. Lin, K. Yu, J. Malik, "Multi-componentmodels for object detection, " in Proc. Eur. Conf. Comput. Vis., 2012, pp. 445-458.
25. T. Hofmann, "Unsupervised learning by probabilistic latentsemantic analysis, " Mach. Learn., vol. 42, no. 1/2, pp. 177-196, 2001.
26. H. Jegou, M. Douze, C. Schmid, "Product quantization fornearest neighbor search, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 33, no. 1, pp. 117-128, Jan. 2011.
27. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, "Caffe: Convolutional architecturefor fast feature embedding, " in arXiv Preprint arXiv:1408. 5093, 2014.
28. G. Kim, A. Torralba, "Unsupervised detection of regions ofinterest using iterative link analysis, " in Proc. Adv. Neural Inf. Process. Syst., 2009, pp. 4-2.
29. A. Krizhevsky, I. Sutskever, G. Hinton, "Imagenet classificationwith deep convolutional neural networks, " in Proc. Adv. NeuralInf. Process. Syst., pp. 1106-1114, 2012.
30. M. P. Kumar, B. Packer, D. Koller, "Self-paced learning forlatent variable models, " in Proc. Adv. Neural Inf. Process. Syst., 2010, pp. 1189-1197.
31. C. Lampert, M. Blaschko, T. Hofmann, "Efficient subwindowsearch: A branch, bound framework for object localization, "IEEE Trans. Pattern Analy. Mach. Intell., vol. 31, no. 12, pp. 2129-2142, Dec. 2009.
32. S. Lazebnik, C. Schmid, J. Ponce, "Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories, "in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2006, pp. 2169-2178.
33. Y. Nesterov, "Smooth minimization of non-smooth functions, "Math. Program., vol. 103, no. 1, pp. 127-152, 2005.
34. M. Nguyen, L. Torresani, F. de la Torre, C. Rother, "Weaklysupervised discriminative localization, classification: A jointlearning process, " in Proc. Int. Conf. Comput. Vis., 2009, pp. 1925-1932.
35. M. Pandey, S. Lazebnik, "Scene recognition, weakly supervisedobject localization with deformable part-based models, " inProc. Int. Conf. Comput. Vis., 2011, pp. 1307-1314.
36. O. Parkhi, A. Vedaldi, C. Jawahar, A. Zisserman, "The truthabout cats, dogs, " in Proc. Int. Conf. Comput. Vis., 2011, pp. 1427-1434.
37. A. Prest, C. Leistner, J. Civera, C. Schmid, V. Ferrari, "Learning object class detectors from weakly annotated video, "Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2012, pp. 3282-3289.
38. O. Russakovsky, Y. Lin, K. Yu, L. Fei-Fei, "Object-centric spatialpooling for image classification, " in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 1-15.
39. J. Sanchez, F. Perronnin, T. Mensink, J. Verbeek, "Image classificationwith the Fisher vector: Theory, practice, " Int. J. Comput. Vis., vol. 105, no. 3, pp. 222-245, 2013.
40. Z. Shi, T. Hospedales, T. Xiang, "Bayesian joint topic modellingfor weakly supervised object localisation, " in Proc. Int. Conf. Comput. Vis., 2013, pp. 2984-2991.
41. Z. Shi, P. Siva, T. Xiang, Q. Mary, "Transfer learning by rankingfor weakly supervised object annotation, " in Proc. Brit. Mach. Vis. Conf., 2012.
42. S. Singh, A. Gupta, A. Efros, "Unsupervised discovery ofmid-level discriminative patches, " in Proc. 12th Eur. Conf. Comput. Vis., 2012, pp. 73-86.
43. P. Siva, C. Russell, T. Xiang, "In defence of negative miningfor annotating weakly labelled data, " in Proc. Eur. Conf. Comput. Vis., 2012, pp. 594-608.
44. P. Siva, C. Russell, T. Xiang, L. Agapito, "Looking beyond theimage: Unsupervised learning for object saliency, detection, "in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2013, pp. 3238-3245.
45. P. Siva, T. Xiang, "Weakly supervised object detector learningwith model drift detection, " in Proc. Int. Conf. Comput. Vis., 2011, pp. 343-350.
46. H. Song, R. Girshick, S. Jegelka, J. Mairal, Z. Harchaoui, T. Darrell, "On learning to localize objects with minimal supervision, "in Proc. Int. Conf. Mach. Learn., 2014, pp. 1611-1619.
47. H. Song, Y. Lee, S. Jegelka, T. Darrell, "Weakly-superviseddiscovery of visual pattern configurations, " in Proc. Adv. NeuralInf. Process. Syst., 2014, pp. 1637-1645.
48. Z. Song, Q. Chen, Z. Huang, Y. Hua, S. Yan, "Contextualizingobject detection, classification, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 1585-1592.
49. J. Uijlings, K. van de Sande, T. Gevers, A. Smeulders, "Selective search for object recognition, " Int. J. Comput. Vis., vol. 104, no. 2, pp. 154-171, 2013.
50. K. van de Sande, C. Snoek, A. Smeulders, "Fisher, VLADwith FLAIR, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2014, pp. 2377-2384.
51. J. Verbeek, B. Triggs, "Region classification with Markov fieldaspect models, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2007, pp. 1-8.
52. S. Vijayanarasimhan, K. Grauman, "Large-scale live activelearning: Training object detectors with crawled data andcrowds, " in Proc. IEEE Conf. Comput. Vis. Pattern Recog., 2011, pp. 1449-1456.
53. C. Wang, W. Ren, K. Huang, T. Tan, "Weakly supervisedobject localization with latent category learning, " in Proc. 13thEur. Conf. Comput. Vis., 2014, pp. 431-445.
54. J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, Y. Gong, "Localityconstrainedlinear coding for image classification, " in Proc. IEEEConf. Comput. Vis. Pattern Recog., 2010, pp. 3360-3367.
55. X. Wang, M. Yang, S. Zhu, Y. Lin, "Regionlets for genericobject detection, " in Proc. Int. Conf. Comput. Vis., 2013, pp. 17-24.
56. C. Zitnick, P. Dollar, "Edge boxes: Locating object proposalsfrom edges, " in Proc. Eur. Conf. Comput. Vis., 2014, pp. 391-405.