Research map / Detection and segmentation / CNN features
Mutual Graph Learning for Camouflaged Object Detection
Qiang Zhai, Xin Li, Fan Yang, Chenglizhao Chen, Hong Cheng, Deng-Ping Fan
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 |
|---|---|---|---|
| Use mutual graph learning with COD and edge extraction | Camouflaged object detection · CHAMELEON | S-measure: 0.869 -> 0.893 | Improved |
| Use mutual graph learning with COD and edge extraction | Camouflaged object detection · CAMO-Test | S-measure: 0.769 -> 0.775 | Improved |
| Use mutual graph learning with COD and edge extraction | Camouflaged object detection · COD10K-Test | S-measure: 0.789 -> 0.814 | Improved |
| Add RIGR to the ResNet-50 FCN baseline (ablation) | MGL · CAMO-Test | S-measure: 0.742 -> 0.766 | Improved |
| Add ECGR to ResNet-50 FCN + RIGR (ablation) | MGL · CAMO-Test | S-measure: 0.766 -> 0.772 | Improved |
| Use K=16 semantic nodes instead of K=32 (ablation) | S-MGL · CAMO-Test | S-measure: 0.771 -> 0.772 | No clear effect |
| Use K=64 semantic nodes instead of K=32 (ablation) | S-MGL · CAMO-Test | S-measure: 0.772 -> 0.774 | No clear effect |
| Use z=16 edge supportive nodes instead of z=32 (ablation) | S-MGL · CAMO-Test | S-measure: 0.772 -> 0.772 | No clear effect |
| Use z=64 edge supportive nodes instead of z=32 (ablation) | S-MGL · CAMO-Test | S-measure: 0.772 -> 0.773 | No clear effect |
| Use two recurrent stages instead of one (ablation) | R-MGL · CAMO-Test | S-measure: 0.772 -> 0.775 | Improved |
| Use three recurrent stages instead of two (ablation) | R-MGL · CAMO-Test | S-measure: 0.775 -> 0.773 | Hurt |
Closest papers by meaning
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection (TPAMI 2024 · similarity 0.85)
- Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection (ICCV 2025 · similarity 0.85)
- Beyond Weak Supervision: MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged Object Detection (CVPR 2026 · similarity 0.85)
- Detecting Objects with Context-Likelihood Graphs and Graph Refinement (ICCV 2023 · similarity 0.85)
- MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes (NeurIPS 2025 · similarity 0.85)
- Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection (CVPR 2024 · similarity 0.84)
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.
