MiNet: Weakly-Supervised Camouflaged Object Detection through Mutual Interaction between Region and Edge Cues

Yuzhen Niu, Lifen Yang, Rui Xu, Yuezhou Li, Yuzhong Chen

Abstract:

Existing weakly-supervised camouflaged object detection (WSCOD) methods have much difficulty in detecting accurate object boundaries due to insufficient and imprecise boundary supervision in scribble annotations. Drawing inspiration from human perception that discerns camouflaged objects by incorporating both object region and boundary information, we propose a novel Mutual Interaction Network (MiNet) for scribble-based WSCOD to alleviate the detection difficulty caused by insufficient scribbles. The proposed MiNet facilitates mutual reinforcement between region and edge cues, thereby integrating more robust priors to enhance detection accuracy. In this paper, we first construct an edge cue refinement net, featuring a core region-aware guidance module (RGM) aimed at leveraging the extracted region feature as a prior to generate the discriminative edge map. By considering both object semantic and positional relationships between edge feature and region feature, RGM highlights the areas associated with the object in the edge feature. Subsequently, to tackle the inherent similarity between camouflaged objects and the surroundings, we devise a region-boundary refinement net. This net incorporates a core edge-aware guidance module (EGM), which uses the enhanced edge map from the edge cue refinement net as guidance to refine the object boundaries in an iterative and multi-level manner. Experiments on CAMO, CHAMELEON, COD10K, and NC4K datasets demonstrate that the proposed MiNet outperforms the state-of-the-art methods.

Primary Subject Area: [Experience] Multimedia Applications

Secondary Subject Area: [Content] Media Interpretation, [Experience] Interactions and Quality of Experience

Relevance To Conference: The task of camouflaged object detection has garnered significant attention due to its potential applications in medical diagnosis, species protection, and crop pest detection. In pursuit of a balance between dataset annotation efficiency and model performance, weakly-supervised camouflaged object detection (WSCOD) based on scribble annotation has been presented and studied. However, existing scribbled-based WSCOD methods have much difficulty in detecting accurate object boundaries due to insufficient and imprecise boundary supervision in scribble annotations. Simultaneously, the high similarity between the camouflaged objects and their surroundings makes it a challenging problem. In the realm of multimedia, the accuracy and precision of camouflaged object detection are crucial for enhancing image and video processing techniques and improving visual experiences. By refining camouflaged object detection algorithms, we can better address the similarity of target objects and backgrounds in multimedia, bringing benefits to a wider range of applications. In order to address the existing challenges of weakly-supervised camouflaged object detection, we propose a novel mutual interaction network for scribble-based WSCOD.

Submission Number: 799