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

Source: [Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage](<https://www.sota2.com/research/paper/68fa76721e209131cea6d0f0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:54:27.044Z

Authors: Yang Hu, Jinxia Zhang, Kaihua Zhang, Yin Yuan, Jiale Huang, Zechao Zhan, Xing Wang

Published: 2024-04-13T09:10:33.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.08936>)

[PDF](<https://arxiv.org/pdf/2404.08936.pdf>)
