Research map / Detection and segmentation / CNN features
I Can Find You! Boundary-Guided Separated Attention Network for Camouflaged Object Detection
Hongwei Zhu, Peng Li, Haoran Xie, Xuefeng Yan, Dong Liang, Dapeng Chen, Mingqiang Wei, Jing Qin
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add separated attention (SEA) (ablation) | BSA-Net baseline · CAMO-Test | Sα: 0.783 -> 0.796 | Improved |
| Add separated attention (SEA) (ablation) | BSA-Net baseline · CHAMELEON | Sα: 0.879 -> 0.882 | Improved |
| Add separated attention (SEA) (ablation) | BSA-Net baseline · COD10K-Test | Sα: 0.805 -> 0.811 | Improved |
| Add boundary guider (BG) (ablation) | BSA-Net baseline · CAMO-Test | Sα: 0.783 -> 0.786 | Improved |
| Add boundary guider (BG) (ablation) | BSA-Net baseline · CHAMELEON | Sα: 0.879 -> 0.875 | Hurt |
| Add boundary guider (BG) (ablation) | BSA-Net baseline · COD10K-Test | Sα: 0.805 -> 0.812 | Improved |
| Add boundary guider (BG) to SEA (ablation) | BSA-Net with SEA · CAMO-Test | Sα: 0.796 -> 0.796 | No clear effect |
| Add boundary guider (BG) to SEA (ablation) | BSA-Net with SEA · CHAMELEON | Sα: 0.882 -> 0.895 | Improved |
| Add boundary guider (BG) to SEA (ablation) | BSA-Net with SEA · COD10K-Test | Sα: 0.811 -> 0.818 | Improved |
| Add SEA (ablation) | BSA-Net baseline · CAMO-Test | MAE: 0.083 -> 0.080 | Improved |
| Add SEA (ablation) | BSA-Net baseline · CHAMELEON | MAE: 0.032 -> 0.030 | Improved |
| Add SEA (ablation) | BSA-Net baseline · COD10K-Test | MAE: 0.037 -> 0.037 | No clear effect |
Closest papers by meaning
- SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection (AAAI 2025 · similarity 0.87)
- Zoom in and Out: A Mixed-Scale Triplet Network for Camouflaged Object Detection (CVPR 2022 · similarity 0.86)
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024 · similarity 0.86)
- Inferring Camouflaged Objects by Texture-Aware Interactive Guidance Network (AAAI 2021 · similarity 0.86)
- FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection (ECCV 2024 · similarity 0.85)
- CamoFormer: Masked Separable Attention for Camouflaged Object Detection (TPAMI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
