Boosting Co-teaching with Compression Regularization for Label Noise

Abstract

In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout. We find that Nested Dropout, though originally proposed to perform fast information retrieval and adaptive data compression, can properly regularize a neural network to combat label noise. Moreover, owing to its simplicity, it can be easily combined with Co-teaching to further boost the performance. Our final model remains simple yet effective: it achieves comparable or even better performance than the state-of-the-art approaches on two real-world datasets with label noise which are Clothing1M and ANIMAL-10N. On Clothing1M, our approach obtains 74.9% accuracy which is slightly better than that of DivideMix. On ANIMAL-10N, we achieve 84.1% accuracy while the best public result by PLC is 83.4%. We hope that our simple approach can be served as a strong baseline for learning with label noise. Our implementation is available at https://github.com/yingyichen-cyy/Nested-Co-teaching.

arXiv commentAccepted by CVPR Workshop 2021. Project page: https://github.com/yingyichen-cyy/Nested-Co-teaching

References in corpus (11)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DivideMix: Learning with Noisy Labels as Semi-supervised Learning
• WebVision Database: Visual Learning and Understanding from Web Data
• Dimensionality-Driven Learning with Noisy Labels
• How does Disagreement Help Generalization against Label Corruption?
• Joint Optimization Framework for Learning with Noisy Labels
• Learning Sparse Networks Using Targeted Dropout
• Probabilistic End-to-end Noise Correction for Learning with Noisy Labels
• Combating noisy labels by agreement: A joint training method with co-regularization
• Learning Ordered Representations with Nested Dropout
• Learning with Feature-Dependent Label Noise: A Progressive Approach