通过混沌边缘优化，提升单域泛化模型的鲁棒性
Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
- 用李雅普诺夫指数动态调节学习率，引导模型训练在混沌边缘
- 在低数据条件下，PACS数据集上提升最高达9.47%
- 适合关注模型鲁棒性和数据稀缺场景的研究者
单域泛化（SDG）旨在仅使用一个源域数据，使模型具备对未见目标域的泛化能力，但面临显著领域偏移和数据多样性不足的挑战。现有方法依赖数据增强，难以有效适应大规模领域偏移下的训练动态。为此，本文提出LEAwareSGD，一种基于李雅普诺夫指数（LE）引导的优化方法，受动力系统理论启发。通过利用LE测量值调节学习率，使模型训练趋近混沌边缘——这一稳定与适应性平衡的关键状态。该动态调整机制使模型探索更广阔的参数空间，捕捉更具泛化性的特征，从而提升整体泛化能力。在PACS、OfficeHome和DomainNet上的大量实验表明，LEAwareSGD实现显著泛化提升，在低数据条件下于PACS上最高取得9.47%的性能增益。结果证实，靠近混沌边缘训练能有效增强SDG任务中的模型泛化能力。
原文摘要 · Abstract (English)
Single Domain Generalization (SDG) aims to develop models capable of generalizing to unseen target domains using only one source domain, a task complicated by substantial domain shifts and limited data diversity. Existing SDG approaches primarily rely on data augmentation techniques, which struggle to effectively adapt training dynamics to accommodate large domain shifts. To address this, we propose LEAwareSGD, a novel Lyapunov Exponent (LE)-guided optimization approach inspired by dynamical systems theory. By leveraging LE measurements to modulate the learning rate, LEAwareSGD encourages model training near the edge of chaos, a critical state that optimally balances stability and adaptability. This dynamic adjustment allows the model to explore a wider parameter space and capture more generalizable features, ultimately enhancing the model's generalization capability. Extensive experiments on PACS, OfficeHome, and DomainNet demonstrate that LEAwareSGD yields substantial generalization gains, achieving up to 9.47\% improvement on PACS in low-data regimes. These results underscore the effectiveness of training near the edge of chaos for enhancing model generalization capability in SDG tasks.
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。