Context-aware Cross-level Fusion Network for Camouflaged Object Detection
This work addresses the challenging problem of detecting camouflaged objects in images, which is important for applications like surveillance and biology, but it appears incremental as it builds on existing COD methods with novel modules.
The paper tackles camouflaged object detection by proposing a Context-aware Cross-level Fusion Network (C2F-Net), which integrates multi-level features and global context to address low boundary contrast and appearance variability, achieving state-of-the-art results on three benchmark datasets.
Camouflaged object detection (COD) is a challenging task due to the low boundary contrast between the object and its surroundings. In addition, the appearance of camouflaged objects varies significantly, e.g., object size and shape, aggravating the difficulties of accurate COD. In this paper, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net) to address the challenging COD task. Specifically, we propose an Attention-induced Cross-level Fusion Module (ACFM) to integrate the multi-level features with informative attention coefficients. The fused features are then fed to the proposed Dual-branch Global Context Module (DGCM), which yields multi-scale feature representations for exploiting rich global context information. In C2F-Net, the two modules are conducted on high-level features using a cascaded manner. Extensive experiments on three widely used benchmark datasets demonstrate that our C2F-Net is an effective COD model and outperforms state-of-the-art models remarkably. Our code is publicly available at: https://github.com/thograce/C2FNet.