抑制与多样化：优化针对自然图像损坏的鲁棒路径
Suppress and Diversify: Refining Robust Pathways for Corruption Robustness
浏览论文内容
中文总结 AI 辅助
该研究针对自然图像损坏的模型鲁棒性问题，提出非侵入式方法S&D，通过选择并多样化鲁棒路径提升性能，在多场景多任务中展现出广泛有效性。
中文摘要 AI 辅助
针对自然图像损坏的模型鲁棒性对安全关键型应用至关重要。现有方法主要聚焦于隐式表示学习，本文首次系统探索计算路径以显式表征内部鲁棒性。我们发现鲁棒特征在网络各层呈现逐步衰减规律，并建立了这些特征的流行度与模型性能间的函数依赖关系。基于该发现，我们提出Suppress and Diversify（S&D），一种非侵入式优化方法，通过动态选择鲁棒路径并利用保对称变换实现路径多样化来提升鲁棒性。S&D与架构无关、无额外参数，且测试时无开销。在8个基准上的大量评估表明，S&D在多视觉任务、多样主干网络及复杂真实场景中均持续提升性能，凸显其广泛有效性与可扩展性。
英文摘要
Model robustness against natural image corruptions is essential for safety-critical applications. While existing methods primarily focus on implicit representation learning, we provide the first systematic exploration of computational pathways to explicitly characterize internal robustness. We identify a progressive decay of robust features across network layers and establish a functional dependency between the prevalence of these features and model performance. To exploit these insights, we propose Suppress and Diversify (S\&D), a non-intrusive refinement approach that enhances robustness by dynamically selecting robust pathways and diversifying them through symmetry-preserving transformations. S\&D is architecture-agnostic, parameter-free, and incurs zero test-time overhead. Extensive evaluations across eight benchmarks demonstrate that S\&D consistently improves performance across multiple vision tasks, diverse backbones, and complex real-world scenarios, highlighting its broad efficacy and scalability.
