Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage

TL;DR

This paper introduces CS$^3$Net, a compact single-branch network for camouflaged object detection that uses a spotlight shifting strategy to improve boundary detection while reducing computational costs.

Contribution

The paper presents a novel single-branch framework with a spotlight shifting strategy and new modules, achieving high performance with lower computational complexity.

Findings

Achieves superior camouflaged object detection performance.

Reduces MACs by 32.13% compared to state-of-the-art methods.

Balances efficiency and effectiveness effectively.

Abstract

Camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the Co-Supervised Spotlight Shifting Network (CS$^3$Net), a compact single-branch framework inspired by how shifting light source exposes camouflage. Our spotlight shifting strategy replaces multi-branch designs by generating supervisory signals that highlight boundary cues. Within CS$^3$Net, a Projection Aware Attention (PAA) module is devised to strengthen feature extraction, while the Extended Neighbor Connection Decoder (ENCD) enhances final predictions. Extensive experiments on public datasets demonstrate that CS$^3$Net not only achieves superior performance, but also reduces Multiply-Accumulate operations (MACs) by 32.13% compared to state-of-the-art COD methods, striking an optimal balance between efficiency and effectiveness.