AINeutralarXiv – CS AI · 3h ago6/10
🧠
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
Researchers propose NCSAM, a novel optimization-based approach to learning from noisy labels that theoretically connects label noise to Sharpness-Aware Minimization's behavior. The method uses noise-compensated perturbations to reduce memorization of corrupted annotations while maintaining optimization simplicity, demonstrating competitive performance against existing noisy-label learning methods.