提出新方法提升噪声标签学习的可靠性，避免用错误信息纠正错误。
Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning
- 分离评估真实标签与伪标签可信度，避免两者相互误导。
- 在合成与真实噪声数据集上显著优于现有基线方法。
- 适合处理标签噪声问题的研究者与实际应用开发者。
基于修复的噪声标签学习将观察到的标签与模型生成的伪目标混合，通常使用单一样本级清洁度分数控制两个分支，导致隐含耦合：降低对真实标签的信任会自动提高对伪目标的信任。我们发现这种互补性可能用一个不可靠信号替换另一个，因为从被污染的监督中学习的伪目标可能重现其本应修正的噪声。表示诊断表明：噪声监督更强烈地影响深层特征，而浅层关系相对稳定，提供损失后验之外的信息。因此，我们提出TRACE框架，用于标签修正与样本重加权。TRACE通过损失拟合、浅层关系稳定性及预测一致性评估真实标签，通过模型置信度单独评估伪目标。其源特定得分在不假设互补可靠性的情况下控制目标修正与监督强度。在合成与真实世界噪声基准上，TRACE改进了代表性修复基线，并生成更可靠的伪监督。
原文摘要 · Abstract (English)
Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches. This creates a hidden coupling: reducing trust in the observed label automatically increases trust in the pseudo target. We show that this complementarity can replace one unreliable signal with another because a pseudo target learned from corrupted supervision may reproduce the noise it is meant to correct. Our representation diagnostics provide a consistent account of this mismatch: noisy supervision redirects deeper layers more strongly, whereas shallower relations remain comparatively stable and provide information beyond the loss posterior. We therefore propose TRACE, a Two-Source Reliability Assessment framework for Label Correction and Sample Reweighting. TRACE assesses the observed label using loss fit, shallow relation stability, and prediction agreement, while separately assessing the pseudo target using model confidence. Its source-specific scores control target correction and supervision strength without assuming complementary reliability. Across synthetic and real-world noisy benchmarks, TRACE improves representative refurbishment baselines and yields more reliable pseudo supervision.
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。