XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
For researchers and practitioners dealing with noisy labeled datasets, XMix provides a robust solution that handles extreme noise and class imbalance without careful tuning.
XMix addresses the problem of learning with extremely noisy labels by leveraging local smoothness in self-supervised feature space to improve sample selection and semi-supervised learning. It outperforms existing methods, achieving state-of-the-art results under high noise levels without requiring prior noise knowledge.
Supervised deep learning models rely on large, accurately labeled datasets, yet noisy annotations are often unavoidable and can severely degrade performance under high noise levels. Recent state-of-the-art methods tackle this by using sample selection strategies that exploit the memorization effect to filter out clean data for semi-supervised learning. However, these methods struggle with extreme noise, class imbalance, and require careful tuning or prior noise knowledge. To address these limitations, we propose XMix, a novel framework that leverages local smoothness in the self-supervised feature space to systematically enhance all stages of the sample selection process, without dependence on potentially corrupted labels. First, XMix estimates the noise rate using maximum likelihood among self-supervised feature neighbors. Second, these neighbors then help identify additional clean samples and ensure balanced selection across classes during sample selection. Finally, in the semi-supervised learning phase, XMix uses neighboring samples to generate more reliable pseudo-labels. Our empirical results show that XMix substantially outperforms existing methods in extremely noisy environments and maintains superior performance in standard LNL benchmarks.