Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909442743730176 |
|---|---|
| author | Hu, Yang Zhang, Jinxia Zhang, Kaihua Yuan, Yin Huang, Jiale Zhan, Zechao Wang, Xing |
| author_facet | Hu, Yang Zhang, Jinxia Zhang, Kaihua Yuan, Yin Huang, Jiale Zhan, Zechao Wang, Xing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08936 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage Hu, Yang Zhang, Jinxia Zhang, Kaihua Yuan, Yin Huang, Jiale Zhan, Zechao Wang, Xing Computer Vision and Pattern Recognition 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. |
| title | Shifting Spotlight for Co-supervision: A Simple yet Efficient Single-branch Network to See Through Camouflage |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.08936 |