用注意力对齐修复模型在噪声等干扰下的表现
AR2: Attention-Guided Repair for the Robustness of CNNs Against Common Corruptions
- 通过对比清晰与受损图像的注意力图，引导模型保持一致关注点
- 在CIFAR和ImageNet的多种干扰测试中，性能优于现有方法
- 无需改模型结构，适合部署在已有CNN上
深度神经网络在遭遇噪声、模糊、天气和数字失真等常见干扰时性能显著下降，限制了其在真实场景中的可靠性。本文提出AR2（注意力引导修复），一种简单有效的预训练CNN抗干扰增强方法。AR2通过显式对齐干净图像与受损图像的类别激活图（CAM），促使模型在输入扰动下仍能保持稳定的注意力分布。该方法采用迭代修复策略，交替进行基于CAM的精炼与标准微调，无需修改网络结构。大量实验表明，AR2在标准干扰基准（CIFAR-10-C、CIFAR-100-C和ImageNet-C）上持续优于现有最先进方法，实现了干净数据精度与抗干扰能力的良好平衡。结果表明，AR2为提升真实环境中模型可靠性提供了鲁棒且可扩展的解决方案。
原文摘要 · Abstract (English)
Deep neural networks suffer from significant performance degradation when exposed to common corruptions such as noise, blur, weather, and digital distortions, limiting their reliability in real-world applications. In this paper, we propose AR2 (Attention-Guided Repair for Robustness), a simple yet effective method to enhance the corruption robustness of pretrained CNNs. AR2 operates by explicitly aligning the class activation maps (CAMs) between clean and corrupted images, encouraging the model to maintain consistent attention even under input perturbations. Our approach follows an iterative repair strategy that alternates between CAM-guided refinement and standard fine-tuning, without requiring architectural changes. Extensive experiments show that AR2 consistently outperforms existing state-of-the-art methods in restoring robustness on standard corruption benchmarks (CIFAR-10-C, CIFAR-100-C and ImageNet-C), achieving a favorable balance between accuracy on clean data and corruption robustness. These results demonstrate that AR2 provides a robust and scalable solution for enhancing model reliability in real-world environments with diverse corruptions.
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。