Is There Really a Camouflaged Object? Towards Realistic Camouflaged Object Detection

2026-08-11

AI Summary

This work addresses the limitation of existing camouflaged object detection methods, which operate under a closed-world assumption and consequently suffer from severe false positives in open-world scenarios containing images without camouflaged objects. To bridge this gap, the authors introduce OPC16K, the first large-scale real-world benchmark dataset that includes negative samples such as pure background and non-camouflaged objects, and propose OPCNet, a presence-aware network that reformulates the task as joint object localization and camouflage existence reasoning. OPCNet incorporates three key components: hierarchical existence reasoning, similarity-aware camouflage relation modeling, and presence-aware feature refinement. Experimental results demonstrate that OPCNet significantly reduces false detection rates on negative samples while maintaining state-of-the-art segmentation accuracy, thereby advancing camouflaged object detection toward practical deployment.

Abstract

Camouflaged object detection (COD) aims to segment objects that are visually concealed in their surroundings and has attracted increasing attention in recent years. However, most existing COD methods are developed under a closed-world assumption, where each input image is assumed to contain a camouflaged object. This assumption ignores realistic scenarios with pure backgrounds or non-camouflaged objects, causing existing models to produce severe false positives when deployed in open-world environments. To address this limitation, we propose OPC16K, a large-scale benchmark for realistic COD. OPC16K contains 16,245 images from 14 sources and is carefully organized into camouflaged-object images, pure background images, and non-camouflaged-object images, enabling comprehensive evaluation of both segmentation quality and negative-sample rejection. Based on this benchmark, we further propose OPCNet, a presence-aware camouflage network that reformulates COD from a pure segmentation task into a joint problem of object localization and camouflage existence reasoning. Specifically, OPCNet introduces hierarchical existence reasoning to distinguish CO, BG, and NOCOD scenarios, similarity-aware camouflage relation modeling to capture foreground-background camouflage cues, and existence-aware feature refinement to regulate segmentation features with existence predictions. Extensive experiments on OPC16K demonstrate that OPCNet achieves superior performance under the proposed realistic COD evaluation protocol, significantly reducing false positives on negative samples while maintaining accurate camouflaged-object segmentation. Code and dataset will be released at https://github.com/2231122/OPCOD.

Problem

• Camouflaged Object Detection
• Open-world
• False Positives
• Negative-sample Rejection
• Realistic Evaluation

Innovation

• camouflaged object detection
• open-world perception
• negative sample rejection
• existence-aware reasoning
• OPC16K benchmark