NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3704
Title:Are Anchor Points Really Indispensable in Label-Noise Learning?


		
Are Anchor Points Really Indispensable in Label-Noise Learning. The author provided a new algorithm to do this based on the idea of anchor points without requiring them. The empirical performance of the method was well-demonstrated and the reviewers are in consensus that this paper should be accepted.