Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage
This addresses efficiency challenges in camouflaged object detection for computer vision applications, though it is incremental as it builds on existing multi-branch designs.
The paper tackles camouflaged object detection by proposing CS$^3$Net, a single-branch network that reduces computational costs while achieving superior performance, cutting Multiply-Accumulate operations by 32.13% compared to state-of-the-art methods.
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.