OAFormer: Occlusion Aware Transformer for Camouflaged Object Detection

Camouflaged object usually have a similar appearance or color to their surrounding environment, so it's difficult to be detected, especially in heavily obscured situations. To deal with this challenge, in this paper, we propose a novel occlusion aware transformer network (OAFormer) to accurately identify the occluded camouflaged object. In OAFormer, a hierarchical location guidance module (HLGM) is designed to locate the potential locations of camouflaged objects. Then, in order to perceive the structural consistency of the occluded object, we design a neighborhood searching module (NSM) to focus on local pixel details of concealed objects. Besides, for each NSM, we take advantages of transformer blocks to capture long-distance dependencies. So our model can easily capture the complete camouflaged object. In the end, we utilize the auxiliary supervision strategy to promote the learning ability of our model. Compared with other state-of-the-art methods, the proposed OAFormer achieves higher accuracy on four challenging datasets. Code and models are available at: https://github.com/xinyang920/OAFormer.