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：摘要：标签噪声是深度学习中的普遍问题，常常损害训练模型的泛化性能。最近，利用特权信息（即在训练时可用但测试时不可得的信息）已成为缓解该问题的有效途径。然而，现有基于特权信息的方法在防止标签噪声过拟合方面，未能持续优于无特权信息的对应方法。为解决这一不足，我们提出Pi-DUAL架构，旨在利用特权信息区分干净标签与错误标签。Pi-DUAL将输出logits分解为基于常规输入特征的预测项和仅受特权信息影响的噪声拟合项。由特权信息引导的门控机制会自适应地调整这两项之间的关注重点，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在关键特权信息基准测试（如ImageNet-PI上提升6.8%）中实现了显著的性能提升，创下新的测试集准确率最高水平。此外，Pi-DUAL是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，可在多种具有特权信息的真实场景中缓解标签噪声的影响。