arXiv:2605.11383cs.CV2026-05

用哈密顿动力学主动修复噪声标签下的分类边界,提升模型鲁棒性。

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

论文配图:HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels
图 1 · 摘自论文原文
  • 基于球面哈密顿蒙特卡洛生成虚拟异常样本,主动重建决策边界。
  • 在CIFAR-10/100和真实噪声数据集上达到当前最优性能。
  • 可无缝接入现有半监督学习框架,适合处理带噪声标签的视觉任务。

在大规模视觉识别与数据挖掘任务中,噪声标签严重削弱深度神经网络(DNN)的泛化能力。现有样本筛选方法主要依赖训练损失或预测置信度进行被动筛选,但在噪声干扰下,特征空间中的决策边界会系统性坍缩,导致模型难以区分难分样本与噪声样本,形成显著性能瓶颈。本研究首次强调主动边界恢复对抗噪声学习的关键作用。提出基于哈密顿动力学的新范式HamBR,核心机制采用球面哈密顿蒙特卡洛(Spherical HMC)主动探测表示空间中的跨类模糊区域,合成高质量虚拟异常样本。通过能量建模施加显式排斥约束,这些合成样本在决策边界处构建稳健的能量屏障,迫使真实样本从重叠分散区域向各自类别中心迁移,从而恢复决策边界的判别锐度。HamBR具备极强通用性,可作为即插即用的防御模块集成至现有半监督噪声标签学习框架。实证表明,该方法显著提升硬边界样本的判别准确率,在CIFAR-10/100及真实噪声基准上取得最先进(SOTA)性能;同时具有更优收敛效率与可靠鲁棒性,并大幅提升模型对分布外(OOD)样本的检测能力。

原文摘要 · Abstract (English)

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.

噪声标签决策边界哈密顿鲁棒学习

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。