C3Net: Context-Contrast Network for Camouflaged Object Detection

TL;DR

C3Net introduces a dual-pathway neural network architecture that effectively addresses the complex challenges of camouflaged object detection by combining edge refinement and contextual localization for state-of-the-art results.

Contribution

The paper presents a novel dual-pathway decoder with specialized modules for edge refinement and contextual localization, advancing camouflaged object detection beyond existing methods.

Findings

Achieves S-measure of 0.898 on COD10K

Achieves S-measure of 0.904 on CAMO

Achieves S-measure of 0.913 on NC4K

Abstract

Camouflaged object detection identifies objects that blend seamlessly with their surroundings through similar colors, textures, and patterns. This task challenges both traditional segmentation methods and modern foundation models, which fail dramatically on camouflaged objects. We identify six fundamental challenges in COD: Intrinsic Similarity, Edge Disruption, Extreme Scale Variation, Environmental Complexities, Contextual Dependencies, and Salient-Camouflaged Object Disambiguation. These challenges frequently co-occur and compound the difficulty of detection, requiring comprehensive architectural solutions. We propose C3Net, which addresses all challenges through a specialized dual-pathway decoder architecture. The Edge Refinement Pathway employs gradient-initialized Edge Enhancement Modules to recover precise boundaries from early features. The Contextual Localization Pathway utilizes our novel Image-based Context Guidance mechanism to achieve intrinsic saliency suppression without external models. An Attentive Fusion Module synergistically combines the two pathways via spatial gating. C3Net achieves state-of-the-art performance with S-measures of 0.898 on COD10K, 0.904 on CAMO, and 0.913 on NC4K, while maintaining efficient processing. C3Net demonstrates that complex, multifaceted detection challenges require architectural innovation, with specialized components working synergistically to achieve comprehensive coverage beyond isolated improvements. Code, model weights, and results are available at https://github.com/Baber-Jan/C3Net.