SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908577370734592 |
|---|---|
| author | Jan, Baber Anwar, Saeed El-Maleh, Aiman H. Siddiqui, Abdul Jabbar Bais, Abdul |
| author_facet | Jan, Baber Anwar, Saeed El-Maleh, Aiman H. Siddiqui, Abdul Jabbar Bais, Abdul |
| contents | Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and multi-scale processors independently. This accumulation creates a computational burden without proportional gains. To manage this complexity, they process at reduced resolutions, eliminating fine details essential for camouflage. We present SPEGNet, addressing fragmentation through a unified design. The architecture integrates multi-scale features via channel calibration and spatial enhancement. Boundaries emerge directly from context-rich representations, maintaining semantic-spatial alignment. Progressive refinement implements scale-adaptive edge modulation with peak influence at intermediate resolutions. This design strikes a balance between boundary precision and regional consistency. SPEGNet achieves 0.887 $S_α$ on CAMO, 0.890 on COD10K, and 0.895 on NC4K, with real-time inference speed. Our approach excels across scales, from tiny, intricate objects to large, pattern-similar ones, while handling occlusion and ambiguous boundaries. Code, model weights, and results are available on \href{https://github.com/Baber-Jan/SPEGNet}{https://github.com/Baber-Jan/SPEGNet}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04472 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection Jan, Baber Anwar, Saeed El-Maleh, Aiman H. Siddiqui, Abdul Jabbar Bais, Abdul Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing Camouflaged object detection segments objects with intrinsic similarity and edge disruption. Current detection methods rely on accumulated complex components. Each approach adds components such as boundary modules, attention mechanisms, and multi-scale processors independently. This accumulation creates a computational burden without proportional gains. To manage this complexity, they process at reduced resolutions, eliminating fine details essential for camouflage. We present SPEGNet, addressing fragmentation through a unified design. The architecture integrates multi-scale features via channel calibration and spatial enhancement. Boundaries emerge directly from context-rich representations, maintaining semantic-spatial alignment. Progressive refinement implements scale-adaptive edge modulation with peak influence at intermediate resolutions. This design strikes a balance between boundary precision and regional consistency. SPEGNet achieves 0.887 $S_α$ on CAMO, 0.890 on COD10K, and 0.895 on NC4K, with real-time inference speed. Our approach excels across scales, from tiny, intricate objects to large, pattern-similar ones, while handling occlusion and ambiguous boundaries. Code, model weights, and results are available on \href{https://github.com/Baber-Jan/SPEGNet}{https://github.com/Baber-Jan/SPEGNet}. |
| title | SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2510.04472 |