Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- information available only during training but not at test time -- has emerged as an effective approach to mitigate this issue. Yet, existing PI-based methods have failed to consistently outperform their no-PI counterparts in terms of preventing overfitting to label noise. To address this deficiency, we introduce Pi-DUAL, an architecture designed to harness PI to distinguish clean from wrong labels. Pi-DUAL decomposes the output logits into a prediction term, based on conventional input features, and a noise-fitting term influenced solely by PI. A gating mechanism steered by PI adaptively shifts focus between these terms, allowing the model to implicitly separate the learning paths of clean and wrong labels. Empirically, Pi-DUAL achieves significant performance improvements on key PI benchmarks (e.g., +6.8% on ImageNet-PI), establishing a new state-of-the-art test set accuracy. Additionally, Pi-DUAL is a potent method for identifying noisy samples post-training, outperforming other strong methods at this task. Overall, Pi-DUAL is a simple, scalable and practical approach for mitigating the effects of label noise in a variety of real-world scenarios with PI.

翻译：标签噪声是深度学习中普遍存在的问题，常损害训练模型的泛化性能。近年来，利用特权信息（PI）——仅在训练时可用而在测试时不可用的信息——已成为缓解此问题的有效方法。然而，现有的基于PI的方法在防止过拟合标签噪声方面未能持续优于不使用PI的方法。为解决这一不足，我们提出了Pi-DUAL，一种旨在利用PI区分干净标签与错误标签的架构。Pi-DUAL将输出logits分解为基于常规输入特征的预测项和仅受PI影响的噪声拟合项。由PI引导的门控机制自适应地在两项之间调整关注点，使模型能够隐式分离干净标签与错误标签的学习路径。实验表明，Pi-DUAL在关键PI基准测试（例如在ImageNet-PI上提升+6.8%）上取得了显著的性能提升，确立了新的最先进测试集准确率。此外，Pi-DUAL是一种在训练后识别噪声样本的有效方法，在此任务上优于其他强基准方法。总体而言，Pi-DUAL是一种简单、可扩展且实用的方法，可在多种具有PI的真实场景中减轻标签噪声的影响。