4.7 Article

Zero-Shot Camouflaged Object Detection

Journal

IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 32, Issue -, Pages 5126-5137

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2023.3308295

Keywords

Camouflaged object detection; zero-shot learn-ing; graph representation

Ask authors/readers for more resources

The goal of this study is to improve the detection performance of unseen classes in camouflaged object detection (COD). A new zero-shot COD framework is proposed, which includes a Dynamic Graph Searching Network (DGSNet) and a Camouflaged Visual Reasoning Generator (CVRG). The framework utilizes a dynamic searching strategy for graph reasoning and aims to detect camouflaged objects more effectively.
The goal of Camouflaged object detection (COD) is to detect objects that are visually embedded in their surroundings. Existing COD methods only focus on detecting camouflaged objects from seen classes, while they suffer from performance degradation to detect unseen classes. However, in a real-world scenario, collecting sufficient data for seen classes is extremely difficult and labeling them requires high professional skills, thereby making these COD methods not applicable. In this paper, we propose a new zero-shot COD framework (termed as ZSCOD), which can effectively detect the never unseen classes. Specifically, our framework includes a Dynamic Graph Searching Network (DGSNet) and a Camouflaged Visual Reasoning Generator (CVRG). In details, DGSNet is proposed to adaptively capture more edge details for boosting the COD performance. CVRG is utilized to produce pseudo-features that are closer to the real features of the seen camouflaged objects, which can transfer knowledge from seen classes to unseen classes to help detect unseen objects. Besides, our graph reasoning is built on a dynamic searching strategy, which can pay more attention to the boundaries of objects for reducing the influences of background. More importantly, we construct the first zero-shot COD benchmark based on the COD10K dataset. Experimental results on public datasets show that our ZSCOD not only detects the camouflaged object of unseen classes but also achieves state-of-the-art performance in detecting seen classes.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available