Boundary-aware Camouflaged Object Detection via Deformable Point Sampling

The camouflaged object detection (COD) task aims to find and segment objects that have a color or texture that is very similar to that of the background. Despite the difficulties of the task, COD is attracting attention in medical, lifesaving, and anti-military fields. To overcome the difficulties of COD, we propose a novel Deformable Point Sampling network (DPS-Net). The proposed network employs a Deformable Point Sampling transformer (DPS transformer) that effectively captures sparse local boundary information of important background-object boundaries in COD using a deformable point sampling method. Furthermore, the proposed DPS transformer demonstrates ro-bust COD performance by extracting context features for target object localization through integrating rough global positional information of objects with boundary local information. Our method is evaluated on three popular datasets and achieves state-of-the-art performance. We prove the effectiveness of the proposed method through comparative experiments.