Lightweight Camouflaged Object Detection Network Based on Feature Complementation and Enhancement

Kangwei Liu, Xiuhong Li, Boyuan Li, Yuye Zhang, Chao Che

Abstract: Recently, CNN-based camouflaged object detection methods are dedicated to improving detection performance, thereby ignoring the huge amount of parameters and computations it brings. And, current methods ignore the importance of the internal consistency of deep features and shallow features for generating discriminative features. To solve the above problems, we propose a novel lightweight network (FCENet) based on feature complementation and enhancement. Firstly, we design the Deep Feature Complementation (DFC) module and Shallow Feature Enhancement (SFE) module to process the deep features and shallow features, respectively. We utilize the DFC module to locate the object and the SFE module to provide more detailed information. Secondly, we design the boundary area enhancement (BAE) module and the feature fusion refinement (FFR) module to strengthen the learning of object boundaries, fuse and refine the enhanced deep and shallow features. Extensive experiments show that compared with existing cutting-edge baselines, our method achieves excellent detection performance at a very low cost (4.67M Parameters, 1.71G FLOPs).