Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

TL;DR

Pi-DUAL is a novel architecture that leverages privileged information during training to effectively distinguish clean from noisy labels, significantly improving accuracy and noise detection in deep learning models.

Contribution

Introduces Pi-DUAL, a new method that uses privileged information to separate clean and noisy labels, outperforming existing approaches in accuracy and noise identification.

Findings

Achieves +6.8% accuracy on ImageNet-PI benchmark.

Outperforms other methods in noisy sample identification.

Establishes new state-of-the-art in label noise mitigation.

Abstract

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.