Channel-Wise Contrastive Learning for Learning with Noisy Labels
This addresses the pervasive issue of noisy labels in real-world datasets, offering a novel method for training more robust classifiers, though it appears incremental as it builds on contrastive learning techniques.
The paper tackles the problem of learning with noisy labels by introducing channel-wise contrastive learning (CWCL) to distinguish authentic label information from noise, achieving superior performance over existing methods on benchmark datasets.
In real-world datasets, noisy labels are pervasive. The challenge of learning with noisy labels (LNL) is to train a classifier that discerns the actual classes from given instances. For this, the model must identify features indicative of the authentic labels. While research indicates that genuine label information is embedded in the learned features of even inaccurately labeled data, it's often intertwined with noise, complicating its direct application. Addressing this, we introduce channel-wise contrastive learning (CWCL). This method distinguishes authentic label information from noise by undertaking contrastive learning across diverse channels. Unlike conventional instance-wise contrastive learning (IWCL), CWCL tends to yield more nuanced and resilient features aligned with the authentic labels. Our strategy is twofold: firstly, using CWCL to extract pertinent features to identify cleanly labeled samples, and secondly, progressively fine-tuning using these samples. Evaluations on several benchmark datasets validate our method's superiority over existing approaches.