One-Class Multiple Instance Learning via Robust PCA for Common Object Discovery
详细信息 查看全文
- 作者：Xinggang Wang (20)
Zhengdong Zhang (21)
Yi Ma (21)
Xiang Bai (20)
Wenyu Liu (20)
Zhuowen Tu (21) (22) - 刊名：Lecture Notes in Computer Science
- 出版年：2013
- 出版时间：2013
- 年：2013
- 卷：7724
- 期：1
- 页码：259-273
- 全文大小：1185KB
- 参考文献：1. Candes, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? Journal of the ACM聽58 (2011)
2. Jolliffe, I.T.: Principal component analysis. Springer (1986)
3. Candes, E., Tao, T.: Near-optimal signal recovery from random projections: universal encoding strategies. IEEE Trans. Inform. Theory聽52, 5406鈥?425 (2005) CrossRef
4. Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: Rasl: Robust alignment by sparse and low-rank decomposition for linearly correlated images. In: CVPR, pp. 763鈥?70 (2010)
5. Dietterich, T.G., Lathrop, R.H.: Solving the multiple-instance problem with axis-parallel rectangles. Artificial Intelligence聽89, 31鈥?1 (1997) CrossRef
6. Zhang, Q., Goldman, S.A.: Em-dd: An improved multiple-instance learning technique. In: Advances in Neural Information Processing Systems, pp. 1073鈥?080. MIT Press (2001)
7. Deselaers, T., Ferrari, V.: A conditional random field for multiple-instance learning. In: Proceedings of the 26th International Conference on Machine Learning (2010)
8. Viola, P., Platt, J.C., Zhang, C.: Multiple instance boosting for object detection. In: Advances in Neural Information Processing Systems, pp. 1419鈥?426. MIT Press (2006)
9. Russell, B.C., Efros, A.A., Sivic, J., Freeman, W.T., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: IEEE Conference on Computer Vision and Pattern Recognition (2006)
10. Lee, Y.J., Grauman, K.: Shape discovery from unlabeled image collections. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)
11. Deselaers, T., Alexe, B., Ferrari, V.: Localizing objects while learning their appearance. ETHZ TR No 276, Eidgenossische Technische Hochschule Zurich (2011)
12. Lin, Z., Chen, M., Wu, L., Ma, Y.: The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices. UIUC Technical Report UILU-ENG-09-2215 (2009)
13. Maron, O., Lozano-Prez, T.: A framework for multiple-instance learning. In: Advances in Neural Information Processing Systems, pp. 570鈥?76. MIT Press (1998)
14. Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: Advances in Neural Information Processing Systems, pp. 561鈥?68. MIT Press (2003)
15. Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE Conference on Computer Vision and Pattern Recognition (2003)
16. Chum, O., Zisserman, A.: An exemplar model for learning object classes. In: IEEE Conference on Computer Vision and Pattern Recognition (2007)
17. Vijayanarasimhan, S., Grauman, K.: Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In: IEEE Conference on Computer Vision and Pattern Recognition (2008)
18. Lee, Y.J., Grauman, K.: Object-graphs for context-aware category discovery. IEEE Transactions on Pattern Analysis and Machine Intelligence, TPAMI (2011)
19. Zhu, L(L.), Lin, C., Huang, H., Chen, Y., Yuille, A.L.: Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol.聽5303, pp. 759鈥?73. Springer, Heidelberg (2008) CrossRef
20. Wu, Y.N., Si, Z., Gong, H., Zhu, S.C.: Learning active basis model for object detection and recognition. International Journal of Computer Vision聽90, 198鈥?35 (2010) CrossRef
21. Rother, C., Minka, T.P., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching - incorporating a global constraint into mrfs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 993鈥?000 (2006)
22. Bagon, S., Brostovski, O., Galun, M., Irani, M.: Detecting and sketching the common. In: IEEE Conference on Computer Vision and Pattern Recognition (2010)
23. Yang, A., Ganesh, A., Sastry, S., Ma, Y.: Fast l1-minimization algorithms and an application in robust face recognition: A review. Technical Report UCB/EECS-2010-13, EECS Department, University of California, Berkeley (2010)
24. Feng, J., Wei, Y., Tao, L., Zhang, C., Sun, J.: Salient object detection by composition. In: International Conference on Computer Vision (2011)
25. Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Transactions on Pattern Analysis and Machine Intelligence聽32 (2010)
26. Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst (2007)
27. Ferrari, V., Tuytelaars, T., Van Gool, L.: Object Detection by Contour Segment Networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol.聽3953, pp. 14鈥?8. Springer, Heidelberg (2006) CrossRef
28. Ferrari, V., Jurie, F., Schmid, C.: From images to shape models for object detection. International Journal of Computer Vision聽87, 284鈥?03 (2010) CrossRef
29. Wang, H., Yang, Q., Zha, H.: Adaptive p-posterior mixture-model kernels for multiple instance learning. In: Proceedings of the 26th International Conference on Machine Learning (2008)
30. Zhou, Z., Sun, Y., Li, Y.: Multi-instance learning by treating instances as noni.i.d. samples. In: Proceedings of the 26th International Conference on Machine Learning (2009)
31. Viola, P., Jones, M.: Robust real-time face detection. International Journal of Computer Vision聽57, 137鈥?54 (2004) CrossRef - 作者单位：Xinggang Wang (20)
Zhengdong Zhang (21)
Yi Ma (21)
Xiang Bai (20)
Wenyu Liu (20)
Zhuowen Tu (21) (22)
20. Huazhong University of Science and Technology, China
21. Visual Computing Group, Microsoft Research Asia, China
22. Lab of Neuro Imaging and Department of Computer Science, UCLA, USA - ISSN：1611-3349
文摘
Principal component analysis (PCA), as a key component in statistical learning, has been adopted in a wide variety of applications in computer vision and machine learning. From a different angle, weakly supervised learning, more specifically multiple instance learning (MIL), allows fine-grained information to be exploited from coarsely-grained label information. In this paper, we propose an algorithm using the robust PCA (RPCA) [1] in a iterative way to perform simultaneous common object discovery and model learning under a one-class multiple instance learning setting. We show the advantage of our method on common object discovery and model learning, which needs no fine/coarse alignment in the input data; in addition, it achieves comparable results with standard two-class MIL learning algorithms but our method is learning from one-class data only.