mlsanityData to 7 Oct 2026

SPEGNet: Synergistic Perception-Guided Network for Camouflaged Object Detection

arXiv 2510.04472 ↗First posted 6 Oct 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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 Sα 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 hrefhttps://github.com/Baber-Jan/SPEGNethttps://github.com/Baber-Jan/SPEGNet.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

33 of 53 references.

References · 33

  1. 2023Segment Anythingcited by 8,158
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  6. 2018Path Aggregation Network for Instance Segmentationcited by 796
  7. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
  8. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  9. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  10. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  11. 2019EGNet:Edge Guidance Network for Salient Object Detectioncited by 237
  12. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
21 more
  1. 2021Concealed Object Detectioncited by 212
  2. 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
  3. 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
  4. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  5. 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
  6. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  7. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  8. 2021Mutual Graph Learning for Camouflaged Object Detectioncited by 103
  9. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 99
  10. 2023Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformerscited by 87
  11. 2021Context-aware Cross-level Fusion Network for Camouflaged Object Detectioncited by 86
  12. 2022High-resolution Iterative Feedback Network for Camouflaged Object Detectioncited by 78
  13. 2024Frequency-Spatial Entanglement Learning for Camouflaged Object Detectioncited by 46
  14. 2023Frequency Perception Network for Camouflaged Object Detectioncited by 37
  15. 2022OSFormer: One-Stage Camouflaged Instance Segmentation with Transformerscited by 30
  16. 2025RUN: Reversible Unfolding Network for Concealed Object Segmentationcited by 28
  17. 2022Boosting Camouflaged Object Detection with Dual-Task Interactive Transformercited by 24
  18. 2024Hierarchical Graph Interaction Transformer with Dynamic Token Clustering for Camouflaged Object Detectioncited by 18
  19. 2024Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2cited by 12
  20. 2022MFSNet: A Multi Focus Segmentation Network for Skin Lesion Segmentationcited by 10
  21. 2025Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuningcited by 3

Built on by

Not cited yet.