Simultaneously Localize, Segment and Rank the Camouflaged Objects

By Yunqiu Lyu, Jing Zhang, Yuchao Dai, Aixuan Li, Bowen Liu, Nick Barnes, Deng-Ping Fan. Computer Vision and Pattern Recognition, 2021

555 citations recorded by the source corpus.

Camouflage is a key defence mechanism across species that is critical to survival. Common strategies for camouflage include background matching, imitating the color and pattern of the environment, and disruptive coloration, disguising body outlines [37]. Camouflaged object detection (COD) aims to segment camouflaged objects hiding in their surroundings. Existing COD models are built upon binary ground truth to segment the camouflaged objects without illustrating the level of camouflage. In this paper, we revisit this task and argue that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can not only lead to a better understanding about camouflage and evolution of animals, but also provide guidance to design more sophisticated camouflage techniques. Furthermore, we observe that it is some specific parts of the camouflaged objects that make them detectable by predators. With the above understanding about camouflaged objects, we present the first ranking based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects. The localization model is proposed to find the discriminative regions that make the camouflaged object obvious. The segmentation model segments the full scope of the camouflaged objects. Further, the ranking model infers the detectability of different camouflaged objects. Moreover, we contribute a large COD testing set to evaluate the generalization ability of COD models. Experimental results show that our model achieves new state-of-the-art, leading to a more interpretable COD network1.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/7ad9c503dbc4bd3a43a7b23b551b8422b2a8ab4a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Deng-Ping Fan
2. Ling Shao
3. Ming-Ming Cheng
4. Ge-Peng Ji
5. Yuchao Dai
6. Jing Zhang
7. Aixuan Li
8. Bowen Liu

In Sensory Systems

1. Ling Shao
2. Deng-Ping Fan
3. Ge-Peng Ji
4. Ming-Ming Cheng
5. Yuchao Dai
6. Jing Zhang
7. Jianbing Shen
8. Wenguan Wang

Citations in the corpus

• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, methodology): “In this way, the SOD models [48, 46, 42, 38] are designed based on both global contrast and local contrast, while the COD models [11, 26, 35, 52, 34] usually avoid searching the camouflaged objects in those salient regions.”
• Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, methodology): “Following [12, 29, 36, 57], we treat COD as a class-independent, pixel-wise segmentation task.”
• Concealed Object Detection (2021, background): “There are also some concurrent works [39], [40], [41] that are accepted”