Top-GAP: Integrating Size Priors in CNNs for more Interpretability, Robustness, and Bias Mitigation
This addresses the need for more interpretable and robust CNNs in computer vision applications, though it appears incremental as it builds on existing regularization and explainability methods.
The paper tackles the problem of improving interpretability, robustness, and bias mitigation in convolutional neural networks by introducing Top-GAP, a regularization technique that constrains feature representation size to focus on salient image regions, resulting in over 50% robust accuracy on CIFAR-10 with PGD attacks and up to 25% improvement in Intersection over Union for object localization.
This paper introduces Top-GAP, a novel regularization technique that enhances the explainability and robustness of convolutional neural networks. By constraining the spatial size of the learned feature representation, our method forces the network to focus on the most salient image regions, effectively reducing background influence. Using adversarial attacks and the Effective Receptive Field, we show that Top-GAP directs more attention towards object pixels rather than the background. This leads to enhanced interpretability and robustness. We achieve over 50% robust accuracy on CIFAR-10 with PGD $ε=\frac{8}{255}$ and $20$ iterations while maintaining the original clean accuracy. Furthermore, we see increases of up to 5% accuracy against distribution shifts. Our approach also yields more precise object localization, as evidenced by up to 25% improvement in Intersection over Union (IOU) compared to methods like GradCAM and Recipro-CAM.