Bilateral decoupling complementarity learning network for camouflaged object detection

doi:10.1016/j.knosys.2025.113158

Return

Bilateral decoupling complementarity learning network for camouflaged object detection

2025-04-01

PRE

DOI：10.1016/j.knosys.2025.113158

Original

Original request for help

Save

Abstract

En 中文

Existing camouflaged object detection methods have made impressive achievements, however, the interference from highly similar backgrounds, as well as the indistinguishable object boundary, still hider the detection accuracy. In this paper, we propose a three-stage bilateral decoupling complementarity learning network (BDCL-Net) to explore how to utilize the specific advantages of multi-level encoded features for achieving high-quality inference. Specifically, all side-output features are decoupled into two branches to generate three complementary features. Different from previous methods that focus on obtaining the camouflaged object and body boundary, our body modeling stage, which includes a global positioning flow (GPF) module and a multi-scale body warping (MBW) module, is deployed to obtain a global contextual feature that provides coarse localization of potential camouflaged objects and a body feature that emphasizes learning the central areas of camouflaged objects. The detail preservation stage is designed to generate a detail feature that pays attention to the regions around the boundary. Consequently, the body prediction can avoid disturbances from the highly similar backgrounds, while the detail prediction can reduce errors caused by imbalanced boundary pixels. The complementary feature integration (CFI) module in the feature aggregation stage is designed to fuse these complementary features in an interactive learning manner. We conduct extensive experiments on four public datasets to demonstrate the effectiveness and superiority of our proposed network. The code is available at http://github.com/iuueong/BDCLNet.

Keywords:

Camouflaged object detection

Decoupling

Complementarity learning

Feature grouping