Countering Noisy Labels By Learning From Auxiliary Clean Labels
This addresses the challenge of noisy labels in machine learning applications, which is an incremental improvement over existing methods.
The paper tackles the problem of learning from noisy labels, including synthetic noise and pseudo labels in semi-supervised learning, by proposing a framework that uses auxiliary clean labels to improve generalization. The result shows that RDCR achieves comparable or superior performance under small noise and significantly outperforms existing methods with large noise.
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.