Learning from massive noisy labeled data for image classification

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Volumn 07-12-June-2015, Issue , 2015, Pages 2691-2699

  Xiao, Tong ^a   Xia, Tian ^b   Yang, Yi ^b   Huang, Chang ^b   Wang, Xiaogang ^a  

^a CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^b BAIDU INC   (China)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION (OF INFORMATION); COMPUTER VISION; NEURAL NETWORKS; PATTERN RECOGNITION;

CLASS LABELS; COMPUTER VISION PROBLEMS; CONVOLUTIONAL NEURAL NETWORK; END TO END; LABELED DATA; NOISY LABELS; PROBABILISTIC GRAPHICAL MODELS; REAL-WORLD;

IMAGE CLASSIFICATION;

EID: 84959207049     PISSN: 10636919     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CVPR.2015.7298885     Document Type: Conference Paper

References (31)

1. H. Azizpour, A. S. Razavian, J. Sullivan, A. Maki, and S. Carlsson. From generic to specific deep representations for visual recognition. arXiv:1406. 5774, 2014. 1,3
2. R. Barandela and E. Gasca. Decontamination of training samples for supervised pattern recognition methods. In ICAPR. 2000. 1,2
3. P. L. Bartlett, M. I. Jordan, and 1. D. McAuliffe. Convexity, classification, and risk bounds. lournal o/the American Statistical Association, 2006
4. E. Beigman and B. B. Klebanov. Learning with annotation noise. In ACL-JJCNLP, 2009
5. C. E. Brodley and M. A. Friedl. Identifying mislabeled training data. arXiv: 1106. 0219, 2011. 1,2
6. J. Deng, W. Dong, R. Socher, L.-l. Li, K. Li, and L. FeiFei. Imagenet: A large-scale hierarchical image database. In CVPR,2009
7. J. Donahue, Y. lia, O. Vinyals, 1. Hoffman, N. Zhang, E. Tzeng, and T. Darrell. Decaf: A deep convolutional activation feature for generic visual recognition. arXiv:1310. 1531, 2013. 1,3
8. c. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. TPAMI, 35(8): 1915-1929,2013
9. B. Frenay and M. Verleysen. Classification in the presence of label noise: a survey. TNNLS, 25(5):845-869, 2014
10. Y. Gong, Q. Ke, M. Isard, and S. Lazebnik. A multi-view embedding space for modeling internet images, tags, and their semantics. JJCV, 106(2):210-233,2014
11. Y. lia, E. Shelhamer, 1. Donahue, S. Karayev, 1. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. In ACM MM, 2014
12. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012.
13. J. Larsen, L. Nonboe, M. Hintz-Madsen, and L. K. Hansen. Design of robust neural network classifiers. In ICASSP, 1998
14. D.-H. Lee. Pseudo-label: The simple and efficient semisupervised learning method for deep neural networks. In ICML Workshop, 2013. 6,8
15. N. Manwani and P. Sastry. Noise tolerance under risk minimization. Cybernetics. IEEE Transactions on, 43(3): 1146-1151,2013
16. N. Matic, I. Guyon, L. Bottou, J. Denker, and V. Vapnik. Computer aided cleaning of large databases for character recognition. In IAPR, 1992
17. A. L. Miranda, L. P. F. Garcia, A. C. Carvalho, and A. C. Lorena. Use of classification algorithms in noise detection and elimination. In HAIS. 2009. 1,2
18. V. Mnih and G. E. Hinton. Learning to label aerial images from noisy data. In ICML, 2012
19. N. Natarajan, I. S. Dhillon, P. K. Ravikumar, and A. Tewari. Learning with noisy labels. In NIPS, 2013
20. D. F. Nettleton, A. Orriols-Puig, and A. Fornells. A study of the effect of different types of noise on the precision of supervised learning techniques. Artificial intelligence review, 33(4):275-306,2010
21. M. Oquab, L. Bottou, I. Laptev, and J. Sivic. Learning and transferring mid-level image representations using convolutional neural networks. In CVPR, 2014. 1,3
22. M. Pechenizkiy, A. Tsymbal, S. Puuronen, and O. Pechenizkiy. Class noise and supervised learning in medical domains: The effect of feature extraction. In CBMS, 2006
23. K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv:1409. 1556, 2014
24. S. Sukhbaatar and R. Fergus. Learning from noisy labels with deep neural networks. arXiv:1406. 2080, 2014. 2,3,4, 6,7,8
25. c. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. arXiv:1409. 4842, 2014
26. C.-M. Teng. A comparison of noise handling techniques. In FLAIRS,2001. 1,2
27. J. Weston, F. Ratle, H. Mobahi, and R. Collobert. Deep learning via semi-supervised embedding. In Neural Networks: Tricks o/the Trade. 2012
28. M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional neural networks. arXiv:1311. 2901, 2013
29. N. Zhang, M. Paluri, M. Ranzato, T. Darrell, and L. Bourdev. Panda: Pose aligned networks for deep attribute modeling. In CVPR,2014
30. X. Zhu and Z. Ghahramani. Learning from labeled and unlabeled data with label propagation. Technical report, Technical Report CMU-CALD-02-107, Carnegie Mellon University, 2002
31. X. Zhu and X. Wu. Class noise vs. attribute noise: A quantitative study. Artificial Intelligence Review, 22(3): 177-210, 2004. 1,2