Fig. 3From: On the role of deep learning model complexity in adversarial robustness for medical imagesSaliency maps of standard trained CBR-LargeT (a, c, e) and Resnet50 (b, d, & f) for Chest X-ray, Dermoscopy & OCT datasets. Unperturbed images with predicted labels and corresponding saliency maps were visualized on row 1 (no attack) for (a–f), respectively. Imperceptibly perturbed images with predicted labels and corresponding saliency maps were visualized on row 2 (PGD attack) for (a–f), respectively. Saliency maps of CBR-LargeT are more concentrated on the regions of interest whereas Resnet50 includes attention regions that are more sporadic on areas that do not contribute to the classification of the diseaseBack to article page