Conference Proceedings

Iterative Learning with Open-set Noisy Labels

Yisen Wang, Weiyang Liu, X Ma, James Bailey, Hongyuan Zha, Le Song, Shu-tao Xia

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition | The Computer Vision Foundation | Published : 2018


Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets are likely to contain noisy (incorrect) labels. Existing works usually employ a closed-set assumption, whereby the samples associated with noisy labels possess a true class contained within the set of known classes in the training data. However, such an assumption is too restrictive for many applications, since samples associated with noisy labels might in fact possess a true class that is not present in the training data. We refer to this more complex scenario as the open-s..

View full abstract


Awarded by National Natural Science Foundation of China

Awarded by NSFC

Awarded by NSF

Awarded by ONR

Funding Acknowledgements

This work is supported by National Natural Science Foundation of China (No. 61771273), NSFC U1609220, NSF IIS-1639792 EAGER, ONR N00014-15-1-2340, Intel ISTC, Amazon AWS and China Scholarship Council (CSC).