提出NCSAM方法，解决噪声标签导致的模型过拟合问题。
NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning
- 从优化角度分析噪声标签对SAM的干扰，设计噪声补偿扰动
- 在合成与真实数据集上优于SAM基线，性能接近主流方法
- 适合需要稳定训练的噪声标签场景，保持优化简洁性
从噪声标签学习（LNL）是深度学习中的基础挑战，因现实数据集常含错误标注。现有方法多依赖标签修正或样本选择，本文从优化视角出发，建立标签噪声与尖锐度感知最小化（SAM）平缓性追求之间的理论联系。基于此，提出噪声补偿的尖锐度感知最小化（NCSAM），采用噪声补偿扰动抵消噪声标签引起的优化偏差。通过修正被扭曲的SAM扰动，NCSAM在训练中减轻对噪声标签的记忆，同时保留基于优化的学习简洁性。在合成及真实世界噪声标签基准上的实验表明，NCSAM持续优于基于SAM的优化基线，并保持与代表性噪声标签学习方法相当的竞争力。
原文摘要 · Abstract (English)
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 (SAM). Based on this analysis, we propose Noise-Compensated Sharpness-Aware Minimization (NCSAM), which uses a noise-compensated perturbation to counteract the optimization bias induced by noisy labels. By correcting distorted SAM perturbations, NCSAM mitigates the memorization of noisy labels during training while preserving the simplicity of optimization-based learning. Experiments on synthetic and real-world noisy-label benchmarks show that NCSAM consistently improves over SAM-based optimization baselines and remains competitive with representative noisy-label learning methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。