通过闭环标签修正提升噪声标签训练效果，兼顾精度与效率。
Robust Self-Training with Closed-loop Label Correction for Learning from Noisy Labels
- 分离式双层优化让分类器与修正函数协同进化
- 在CIFAR和Clothing1M上达到最优性能且训练更快
- 适合有噪声标签数据的实用场景，尤其资源受限时
使用噪声标签训练深度神经网络仍面临巨大挑战，常导致性能下降。现有方法多依赖转移矩阵、噪声检测或元学习，但往往对噪声样本利用不足且计算成本高。本文提出一种基于解耦双层优化的自训练标签修正框架，使分类器与神经修正函数共同演化。借助小规模干净数据集，通过噪声后验模拟和中间特征传递真实标签知识，构建闭环反馈系统以防止错误累积。理论分析保证了方法稳定性，大量实验在CIFAR和Clothing1M等基准数据集上验证了其先进性能并显著缩短训练时间，凸显其在噪声标签学习中的实际应用价值。
原文摘要 · Abstract (English)
Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning techniques, but they often exhibit low utilization efficiency of noisy samples and incur high computational costs. In this paper, we propose a self-training label correction framework using decoupled bilevel optimization, where a classifier and neural correction function co-evolve. Leveraging a small clean dataset, our method employs noisy posterior simulation and intermediate features to transfer ground-truth knowledge, forming a closed-loop feedback system that prevents error amplification. Theoretical guarantees underpin the stability of our approach, and extensive experiments on benchmark datasets like CIFAR and Clothing1M confirm state-of-the-art performance with reduced training time, highlighting its practical applicability for learning from noisy labels.
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。