Simultaneously Localize, Segment and Rank the Camouflaged Objects

Abstract

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 [35]. 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. And, 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 network.

arXiv commentAccepted to IEEE/CVF CVPR 2021. Our code and dataset are publicly available at https://github.com/JingZhang617/COD-Rank-Localize-and-Segment

References in corpus (5)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Anabranch Network for Camouflaged Object Segmentation
• Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network
• Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency

Cited by in corpus (6)

• Concealed Object Detection
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
• Advances in Deep Concealed Scene Understanding
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
• Improving Camouflaged Object Detection with the Uncertainty of Pseudo-edge Labels
• Utilizing Grounded SAM for self-supervised frugal camouflaged human detection