AR2: Attention-Guided Repair for the Robustness of CNNs Against Common Corruptions
This addresses the reliability issue for CNNs in real-world applications with diverse corruptions, representing an incremental improvement over existing methods.
The paper tackled the problem of deep neural networks' performance degradation under common corruptions like noise and blur, proposing AR2 to enhance robustness by aligning class activation maps between clean and corrupted images, resulting in consistent outperformance of state-of-the-art methods on benchmarks such as CIFAR-10-C and ImageNet-C.
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.