NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning

ArXi:2601.19947v2 Announce Type: replace-cross Learning from Noisy Labels (LNL) remains a fundamental challenge in deep learning because real-world datasets often contain corrupted annotations. Most existing methods rely on label correction or sample selection mechanisms. In contrast, we study LNL from an optimization perspective by establishing a theoretical connection between label noise and the flatness-seeking behavior of Sharpness-Aware Minimization