Camouflaged Object Detection via Context-Aware Cross-Level Fusion

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and large variation appearances, e.g., size shape. To address these challenges, we propose novel Context-aware Cross-level Fusion Network ( $\text{C}^{2}\text{F}$ -Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, compute informative attention coefficients multi-level our Attention-induced Module (ACFM), further integrates under guidance coefficients. We then Dual-branch Global Context (DGCM) refine fused feature representations by exploiting rich global context information. Multiple ACFMs DGCMs are integrated cascaded manner generating coarse prediction high-level features. The acts as an map low-level before passing them Camouflage Inference (CIM) generate final prediction. perform extensive experiments on three widely used benchmark datasets compare -Net state-of-the-art (SOTA) models. results show is effective model outperforms SOTA models remarkably. Further, evaluation polyp segmentation demonstrates promising potentials downstream applications. Our code publicly available at: https://github.com/Ben57882/C2FNet-TSCVT