提出新方法让模型在错误标签下仍能准确分类。
Robust Classification with Noisy Labels Based on Posterior Maximization
- 用后验最大化修正噪声标签下的损失函数。
- 证明该方法对对称噪声完全鲁棒，无需额外修正。
- 适合处理真实数据中常见标签错误的场景。
设计对标签噪声鲁棒的目标函数对实际分类算法至关重要。本文研究了近期提出的基于f-散度的分类目标函数（称为f-PML）在标签噪声下的鲁棒性。我们发现，任何f-PML目标函数在标签噪声存在时均可通过校正获得与使用干净数据训练的神经网络等价的结果。此外，我们提出一种新的测试阶段修正方法，可对噪声训练后得到的后验分布进行精炼。我们进一步证明，即使f-PML目标函数本身不对称，它们对任意f-散度均对称标签噪声具有鲁棒性，无需校正。这使得交叉熵（属于f-PML类）也对对称标签噪声具备鲁棒性。最后，该类目标函数结合优化训练策略，性能可媲美现有最先进的噪声标签分类技术。
原文摘要 · Abstract (English)
Designing objective functions robust to label noise is crucial for real-world classification algorithms. In this paper, we investigate the robustness to label noise of an $f$-divergence-based class of objective functions recently proposed for supervised classification, herein referred to as $f$-PML. We show that, in the presence of label noise, any of the $f$-PML objective functions can be corrected to obtain a neural network that is equal to the one learned with the clean dataset. Additionally, we propose an alternative and novel correction approach that, during the test phase, refines the posterior estimated by the neural network trained in the presence of label noise. Then, we demonstrate that, even if the considered $f$-PML objective functions are not symmetric, they are robust to symmetric label noise for any choice of $f$-divergence, without the need for any correction approach. This allows us to prove that the cross-entropy, which belongs to the $f$-PML class, is robust to symmetric label noise. Finally, we show that such a class of objective functions can be used together with refined training strategies, achieving competitive performance against state-of-the-art techniques of classification with label noise.
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。