Sample Prior Guided Robust Model Learning to Suppress Noisy Labels
arXiv:2112.01197
Abstract
Imperfect labels are ubiquitous in real-world datasets and seriously harm the model performance. Several recent effective methods for handling noisy labels have two key steps: 1) dividing samples into cleanly labeled and wrongly labeled sets by training loss, 2) using semi-supervised methods to generate pseudo-labels for samples in the wrongly labeled set. However, current methods always hurt the informative hard samples due to the similar loss distribution between the hard samples and the noisy ones. In this paper, we proposed PGDF (Prior Guided Denoising Framework), a novel framework to learn a deep model to suppress noise by generating the samples' prior knowledge, which is integrated into both dividing samples step and semi-supervised step. Our framework can save more informative hard clean samples into the cleanly labeled set. Besides, our framework also promotes the quality of pseudo-labels during the semi-supervised step by suppressing the noise in the current pseudo-labels generating scheme. To further enhance the hard samples, we reweight the samples in the cleanly labeled set during training. We evaluated our method using synthetic datasets based on CIFAR-10 and CIFAR-100, as well as on the real-world datasets WebVision and Clothing1M. The results demonstrate substantial improvements over state-of-the-art methods.
References in corpus (13)
- mixup: Beyond Empirical Risk Minimization
- Recent Trends in Deep Learning Based Natural Language Processing
- Understanding deep learning requires rethinking generalization
- Learning to Reweight Examples for Robust Deep Learning
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- WebVision Database: Visual Learning and Understanding from Web Data
- Early-Learning Regularization Prevents Memorization of Noisy Labels
- How does Disagreement Help Generalization against Label Corruption?
- Curriculum Loss: Robust Learning and Generalization against Label Corruption
- LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
- L_DMI: An Information-theoretic Noise-robust Loss Function
- Deep Self-Learning From Noisy Labels
- Augmentation Strategies for Learning with Noisy Labels