Similarity activation map for co-salient object detection

Co-salient object detection aims to detect the common objects within a group of relevant images, to which the spatial similarity contributes a lot. Existing methods utilize the inner product to compute the pixel-wise correlations, imitating the tracking methods. We present a novel yet effective module (Similarity Activation Module, SAM) to generate the similarity activation maps as the spatial modulator. The similarity activation maps are learned to highlight the common objects across the multiple images while suppressing other objects and the background. Moreover, we propose the Edge Extraction Module (EEM) and Feature Fusion Module (FFM) which can be easily applied to any existing methods without requiring architectural changes. Extensive experiments on different co-salient detection datasets demonstrate that our method (SimiNet) achieves state-of-the-art performance under various evaluation metrics.