Integrating Part-Object Relationship and Contrast for Camouflaged Object Detection

Problem Statement

Object detectors that solely rely on image contrast are struggling to detect camouflaged objects in images because of the high similarity between camouflaged objects and their surroundings.

To address this issue, in this paper, we investigate the role of the part-object relationship for camouflaged object detection.

Proposed Method: POCINet

Specifically, we propose a Part-Object relationship and Contrast Integrated Network (POCINet) covering both search and identification stages, where each stage adopts an appropriate scheme to engage the contrast information and part-object relational knowledge for camouflaged pattern decoding.

Besides, we bridge these two stages via a Search-to-Identification Guidance (SIG) module, in which the search result, as well as decoded semantic knowledge, jointly enhances the features encoding ability of the identification stage.

Experimental Results

Experimental results demonstrate the superiority of our algorithm on three datasets. Notably, our algorithm raises Fβ of the best existing method by approximately 17 points on the CPD1K dataset.

The integration of part-object relationships with contrast information provides a powerful framework for detecting highly camouflaged objects that traditional contrast-based methods struggle to identify.

The source code will be released soon.