Knowledge-Based Topic Model for Unsupervised Object Discovery and Localization

IEEE Transactions on Image Processing

Volumn 27, Issue 1, 2018, Pages 50-63

  Niu, Zhenxing ^a   Hua, Gang ^b   Wang, Le ^c   Gao, Xinbo ^a  

^a XIDIAN UNIVERSITY   (China)

^b MICROSOFT RESEARCH   (United States)

^c XI'AN JIAOTONG UNIVERSITY   (China)

Author keywords

latent Dirichlet allocation; Object discovery; object localization; topic model

Indexed keywords

BUILDINGS; COHERENT LIGHT; FLOW VISUALIZATION; IMAGE SEGMENTATION; KNOWLEDGE BASED SYSTEMS; OBJECT RECOGNITION; SEMANTICS; STATISTICS;

COMPUTATIONAL MODEL; LATENT DIRICHLET ALLOCATION; OBJECT DISCOVERY; OBJECT LOCALIZATION; RESOURCE MANAGEMENT; TOPIC MODELING;

DATA MINING;

ARTICLE; COMPUTER MODEL; CONTROLLED STUDY; IMAGE SEGMENTATION; INTERNET; NONHUMAN; RESOURCE MANAGEMENT; SEMANTICS; VANILLA;

EID: 85023762973     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIP.2017.2718667     Document Type: Article

References (40)

1. 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, Dec. 2012.
2. A. Joulin, F. Bach, and J. Ponce, "Discriminative clustering for image co-segmentation, " in Proc. CVPR, Jun. 2010, pp. 1943-1950.
3. J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman, "Discovering objects and their location in images, " in Proc. ICCV, Oct. 2005, pp. 370-377.
4. 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. CVPR, Jun. 2006, pp. 1605-1614.
5. T. Hofmann, "Unsupervised learning by probabilistic latent semantic analysis, " Mach. Learn., vol. 42, no. 1, pp. 177-196, Jan. 2001.
6. D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent Dirichlet allocation, " J. Mach. Learn. Res., vol. 3, pp. 993-1022, Mar. 2003.
7. J. Chang, J. L. Boyd-Graber, W. Chong, S. Gerrish, and D. M. Blei, "Reading tea leaves: How humans interpret topic models, " in Proc. NIPS, 2009, pp. 288-296.
8. D. Mimno, H. M. Wallach, E. Talley, M. Leenders, and A. McCallum, "Optimizing semantic coherence in topic models, " in Proc. EMNLP, 2011, pp. 262-272.
9. Z. Chen, A. Mukherjee, B. Liu, M. Hsu, M. Castellanos, and R. Ghosh, "Leveraging multi-domain prior knowledge in topic models, " in Proc. IJCAI, 2013, pp. 2071-2077.
10. D. Andrzejewski, X. Zhu, and M. Craven, "Incorporating domain knowledge into topic modeling via Dirichlet forest priors, " in Proc. ICML, 2009, pp. 25-32.
11. A. Mukherjee and B. Liu, "Aspect extraction through semi-supervised modeling, " in Proc. ACL, 2012, pp. 339-348.
12. J. Yuan, G. Zhao, Y. Fu, Z. Li, A. K. Katsaggelos, and Y. Wu, "Discovering thematic objects in image collections and videos, " IEEE Trans. Image Process., vol. 21, no. 4, pp. 2207-2219, Apr. 2012.
13. G. Kim, C. Faloutsos, and M. Hebert, "Unsupervised modeling of object categories using link analysis techniques, " in Proc. CVPR, Jun. 2008, pp. 1-8.
14. 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, 2010.
15. A. Faktor and M. Irani, "'Clustering by composition'-Unsupervised discovery of image categories, " IEEE Trans. Pattern Anal. Mach. Intell., vol. 36, no. 6, pp. 1092-1106, Jun. 2014.
16. H. Wang, J. Yuan, and Y. Wu, "Context-aware discovery of visual co-occurrence patterns, " IEEE Trans. Image Process., vol. 23, no. 4, pp. 1805-1819, Apr. 2014.
17. K. Grauman and T. Darrell, "Unsupervised learning of categories from sets of partially matching image features, " in Proc. CVPR, Jun. 2006, pp. 19-25.
18. Y. J. Lee and K. Grauman, "Foreground focus: Finding meaningful features in unlabeled images, " in Proc. BMVC, 2008, pp. 1-10.
19. G. Kim and A. Torralba, "Unsupervised detection of regions of interest using iterative link analysis, " in Proc. NIPS, 2009, pp. 961-969.
20. J. Jagarlamudi, H. Daumé, III, and R. Udupa, "Incorporating lexical priors into topic models, " in Proc. EACL, 2012, pp. 204-213.
21. Z. Chen, A. Mukherjee, B. Liu, M. Hsu, M. Castellanos, and R. Ghosh, "Discovering coherent topics using general knowledge, " in Proc. CIKM, 2013, pp. 209-218.
22. R. G. Cinbis, J. Verbeek, and C. Schmid, "Multi-fold MIL training for weakly supervised object localization, " in Proc. CVPR, Jun. 2014, pp. 2409-2416.
23. C. Doersch, A. Gupta, and A. A. Efros, "Context as supervisory signal: Discovering objects with predictable context, " in Proc. ECCV, 2014, pp. 362-377.
24. S. Singh, A. Gupta, and A. A. Efros, "Unsupervised discovery of midlevel discriminative patches, " in Proc. ECCV, 2012, pp. 73-86.
25. C. Wang, K. Huang, W. Ren, J. Zhang, and S. Maybank, "Largescale weakly supervised object localization via latent category learning, " IEEE Trans. Image Process., vol. 24, no. 4, pp. 1371-1385, Apr. 2015.
26. M. Cho, S. Kwak, C. Schmid, and J. Ponce, "Unsupervised object discovery and localization in the wild: Part-based matching with bottomup region proposals, " in Proc. CVPR, Jun. 2015, pp. 1201-1210.
27. M. Rubinstein, J. Kopf, C. Liu, and A. Joulin, "Unsupervised joint object discovery and segmentation in Internet images, " in Proc. CVPR, Jun. 2013, pp. 1939-1946.
28. K. Tang, A. Joulin, L. Fei-Fei, and L.-J. Li, "Co-localization in realworld images, " in Proc. CVPR, Jun. 2014, pp. 1464-1471.
29. A. Joulin, K. Tang, and L. Fei-Fei, "Efficient image and video co-localization with Frank-Wolfe algorithm, " in Proc. ECCV, 2014, pp. 253-268.
30. K. Pearson, "Note on regression and inheritance in the case of two parents, " in Proc. Roy. Soc. London, vol. 58, pp. 240-242, Jan. 1895.
31. S. Y. Dennis, III, "On the hyper-Dirichlet type 1 and hyper-Liouville distributions, " Commun. Statist. Theory Methods, vol. 20, no. 12, pp. 4069-4081, 1991.
32. S. Y. Dennis, III, "A Bayesian analysis of tree-structured statistical decision problems, " J. Statist. Planning Inference, vol. 53, no. 3, pp. 323-344, 1996.
33. T. L. Griffiths and M. Steyvers, "Finding scientific topics, " Proc. Nat. Acad. Sci. USA, vol. 101, no. 1, pp. 5228-5235, 2004.
34. Z. Niu, G. Hua, X. Gao, and Q. Tian, "Semi-supervised relational topic model for weakly annotated image recognition in social media, " in Proc. CVPR, Jun. 2014, pp. 4233-4240.
35. W. Chong, D. Blei, and F.-F. Li, "Simultaneous image classification and annotation, " in Proc. ICCV, Jun. 2005, pp. 1903-1910.
36. L. Fei-Fei and P. Perona, "A Bayesian hierarchical model for learning natural scene categories, " in Proc. CVPR, Jun. 2005, pp. 524-531.
37. D. G. Lowe, "Object recognition from local scale-invariant features, " in Proc. ICCV, Sep. 1999, pp. 1150-1157.
38. J. Shi and J. Malik, "Normalized cuts and image segmentation, " in Proc. ICCV, Jun. 1997, pp. 1-7.
39. J. Sivic and A. Zisserman, "Video Google: A text retrieval approach to object matching in videos, " in Proc. ICCV, Oct. 2003, pp. 1470-1477.
40. L. van der Maaten and G. Hinton, "Visualizing data using t-SNE, " J. Mach. Learn. Res., vol. 9, no. 11, pp. 2579-2605, 2008.