Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels

14 Jun 2020  ·  Songhua Wu, Xiaobo Xia, Tongliang Liu, Bo Han, Mingming Gong, Nannan Wang, Haifeng Liu, Gang Niu ·

Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class label or not. Through this transformation, the reduction of the noise rate is theoretically guaranteed, and hence it is in principle easier to handle noisy similarity labels. Amazingly, DNNs that predict the clean class labels can be trained from noisy data pairs if they are first pretrained from noisy data points. Class2Simi is computationally efficient because not only this transformation is on-the-fly in mini-batches, but also it just changes loss computation on top of model prediction into a pairwise manner. Its effectiveness is verified by extensive experiments.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here