LongReMix: Robust learning with high confidence samples in a noisy label environment

作者：

Highlights：

• We propose a new two-stage noisy-label learning algorithm, called LongReMix.

• The first stage finds a highly precise, but potentially small, set of clean samples.

• The second stage is designed to be robust to small sets of clean samples.

• LongReMix reaches SOTA performance on the main noisy-label learning benchmarks.

摘要

•We propose a new two-stage noisy-label learning algorithm, called LongReMix.•The first stage finds a highly precise, but potentially small, set of clean samples.•The second stage is designed to be robust to small sets of clean samples.•LongReMix reaches SOTA performance on the main noisy-label learning benchmarks.

论文关键词：Noisy label learning,Deep learning,Empirical vicinal risk,Semi-supervised learning

论文评审过程：Received 14 April 2022, Revised 11 August 2022, Accepted 27 August 2022, Available online 2 September 2022, Version of Record 12 September 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.109013