HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels

TL;DR

HamBR introduces a Hamiltonian dynamics-based method to actively restore decision boundaries in noisy label learning, significantly improving robustness and accuracy in visual recognition tasks.

Contribution

This work pioneers the use of Hamiltonian dynamics for active boundary restoration, enhancing noise-robust learning in deep neural networks.

Findings

Achieves state-of-the-art accuracy on CIFAR-10/100 with noisy labels.

Enhances OOD detection and convergence efficiency.

Effectively restores decision boundary sharpness in noisy environments.

Abstract

In large-scale visual recognition and data mining tasks, the presence of noisy labels severely undermines the generalization capability of deep neural networks (DNNs). Prevalent sample selection methods rely primarily on training loss or prediction confidence for passive screening. However, within a feature space degraded by noise, decision boundaries undergo systematic boundary collapse. This phenomenon hinders the ability of the model to distinguish between hard clean samples and noisy samples at the decision margins, thereby creating a significant performance bottleneck. This study is the first to emphasize the pivotal importance of active boundary restoration for noise-robust learning. We propose HamBR, a novel paradigm based on Hamiltonian dynamics. The core approach leverages the Spherical Hamiltonian Monte Carlo (Spherical HMC) mechanism to actively probe inter-class ambiguous regions within the representation space and synthesize high-quality virtual outliers. By imposing explicit repulsion constraints via energy-based modeling, these synthesized samples establish robust energy barriers at the decision boundaries. This mechanism forces real samples to move from dispersed overlapping regions toward their respective class centers, thereby restoring the discriminative sharpness of the decision boundaries. HamBR demonstrates exceptional versatility and can be integrated as a plug-and-play defense module into existing semi-supervised noisy label learning frameworks. Empirical evaluations show that the proposed paradigm significantly enhances the discriminative accuracy of hard boundary samples, achieving state-of-the-art (SOTA) performance on CIFAR-10/100 and real-world noise benchmarks. Furthermore, it exhibits superior convergence efficiency and reliable robustness, while improving significantly the capability of the model for Out-of-Distribution (OOD) detection.