Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of observed labels could result in a loss of information, especially when the corruption is not completely random, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: Pseudo-labels fail to correct a considerable amount of noisy labels and consequently, the errors accumulate. To sufficiently exploit information from observed labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR)-a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art results across datasets and noise types. For example, Robust LR achieves up to 4.5% absolute top-1 accuracy improvement over the previous best on the real-world noisy dataset WebVision.

通过融合伪标记和置信度估计技术，Robust LR 方法成功地改善了数据标签噪声和确认偏差，并在以不同级别合成噪声的 CIFAR 和真实噪声的 Mini-WebVision 和 ANIMAL-10N 三个数据集上实现了最先进的性能。

学习中的确认偏见问题：以标签噪声为手段进行打击