"Zero-Shot Camouflaged Object Detection" by Haoran Li, Chun Mei Feng et al.
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 pro...
Dynamic Graph Searching Network Dgsnet Dynamic Graph Searching Network Camouflaged Visual Reasoning Generator Camouflaged Object Detection Graph Representation Zero Shot Learning
Source: uow.edu.au