Countering Noisy Labels By Learning From Auxiliary Clean Labels
arXiv:1905.13305
Abstract
We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we also consider the pseudo labels in semi-supervised learning (Semi-SL) as a special case of NL. For both types of noise, we argue that the generalization performance of existing methods is highly coupled with the quality of noisy labels. Therefore, we counter the problem from a novel and unified perspective: learning from the auxiliary clean labels. Specifically, we propose the Rotational-Decoupling Consistency Regularization (RDCR) framework that integrates the consistency-based methods with the self-supervised rotation task to learn noise-tolerant representations. The experiments show that RDCR achieves comparable or superior performance than the state-of-the-art methods under small noise, while outperforms the existing methods significantly when there is large noise.
References in corpus (17)
- On the difficulty of training Recurrent Neural Networks
- Instance Normalization: The Missing Ingredient for Fast Stylization
- Wide Residual Networks
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Learning to Reweight Examples for Robust Deep Learning
- Learning with Pseudo-Ensembles
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Rotation equivariant vector field networks
- Dimensionality-Driven Learning with Noisy Labels
- Unsupervised Label Noise Modeling and Loss Correction
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
- Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
- High-Fidelity Image Generation With Fewer Labels
- Robust Inference via Generative Classifiers for Handling Noisy Labels
- Wasserstein Adversarial Regularization (WAR) on label noise
- A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR