Edge-guided Contextual Attention Fusion Network for Camouflaged Object Detection

Camouflaged object detection (COD), with the aim of detecting camouflaged objects from similar backgrounds, is a rewarding but challenging task. A major challenge is that intrinsic similarity between foreground object and background surroundings makes existing methods based on CNNs difficult to accurately identify objects. For that purpose, we propose a novel edge-guided contextual attention fusion network (ECAFNet) in this paper. Specifically, instead of using traditional CNN encoder, we adopt an effective transformer encoder, which can learn more robust and precise representations for the image features. Besides, we introduce three novel modules including edge generation module (EGM) to get object edges for more accurate segmentation of objects, edge-guided receptive field module (ERFM) to enlarge receptive field to capture more robust features, and contextual attention fusion module (CAFM) to closely fuse multiscale features. Extensive experiments on three challenging benchmark datasets indicate that the proposed ECAFNet is an efficient COD method and significantly surpasses the state-of-the-art models.