研究人员开发了一种新的自适应框架，用于检测用于训练深度神经网络的数据集中的噪声标签。该方法整合了局部、全局和学习动态线索，无需手动阈值或噪声水平的先验知识即可稳健地识别损坏的数据。在各种数据集上的实验表明，即使存在显著的标签噪声，召回率也很高，从而提高了模型准确性。 AI
影响 通过实现更准确的训练数据清洗来提高AI模型的鲁棒性。
排序理由 该集群包含一篇详细介绍机器学习中噪声标签检测新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.07086v1 Announce Type: cross Abstract: Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets. In real-world applications, however, labels are often corrupted by ambiguity, human error, or dynamic environments. Over-parameterized DNNs…
Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets. In real-world applications, however, labels are often corrupted by ambiguity, human error, or dynamic environments. Over-parameterized DNNs easily memorize these noisy labels during trainin…