Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion

Abstract

Deep neural networks need large amounts of labeled data to achieve good performance. In real-world applications, labels are usually collected from non-experts such as crowdsourcing to save cost and thus are noisy. In the past few years, deep learning methods for dealing with noisy labels have been developed, many of which are based on the small-loss criterion. However, there are few theoretical analyses to explain why these methods could learn well from noisy labels. In this paper, we theoretically explain why the widely-used small-loss criterion works. Based on the explanation, we reformalize the vanilla small-loss criterion to better tackle noisy labels. The experimental results verify our theoretical explanation and also demonstrate the effectiveness of the reformalization.

arXiv commentAccepted to International Joint Conference on Artificial Intelligence (IJCAI) 2021, includes non-archival supplementary material

References in corpus (8)

• Deep Learning is Robust to Massive Label Noise
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• WebVision Database: Visual Learning and Understanding from Web Data
• Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels
• Learning with Bad Training Data via Iterative Trimmed Loss Minimization
• Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
• L_DMI: An Information-theoretic Noise-robust Loss Function
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning