ABSTRACT
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide pixel-level localization, but their focus tends to be restricted to a small discriminative region of the target object. AdvCAM is an attribution map of an image that is manipulated to increase the classification score produced by a classifier. This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in the opposite directions from those used in an adversarial attack. This process enhances non-discriminative yet class-relevant features, which used to make an insufficient contribution to previous attribution maps, so that the resulting AdvCAM identifies more regions of the target object. In addition, we introduce a new regularization procedure that inhibits the incorrect attribution of regions unrelated to the target object and the excessive concentration of attributions on a small region of the target object. In weakly and semi-supervised semantic segmentation, our method achieved a new state-of-the-art performance on both the PASCAL VOC and MS COCO datasets. In weakly supervised object localization, it achieved a new state-of-the-art performance on the CUB-200-2011 and ImageNet-1K datasets.
