Research map / Detection and segmentation / CNN features
Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection
Fan Yang, Qiang Zhai, Xin Li, Rui Huang, Ao Luo, Hong Cheng, Deng-Ping Fan
Read the paperCheck your idea against 137,217 papers
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 uncertainty-guided transformer (UGT) on top of UQN (ablation) | UGTR · COD10K-Test | S-measure: 0.730 -> 0.789 | Improved |
| add uncertainty-guided transformer (UGT) on top of UQN (ablation) | UGTR · CAMO-Test | S-measure: 0.728 -> 0.747 | Improved |
| add prototyping transformer (PT) to UGT (ablation) | UGTR · COD10K-Test | S-measure: 0.789 -> 0.818 | Improved |
| add prototyping transformer (PT) to UGT (ablation) | UGTR · CAMO-Test | S-measure: 0.747 -> 0.785 | Improved |
| replace UQN probabilistic network with deterministic ResNet50-FCN (ablation) | UGTR · CAMO-Test | S-measure: 0.742 vs 0.728 | No clear effect |
| use PT instead of global average pooling for high-level semantics (ablation) | UGTR · COD10K-Test | S-measure: 0.776 -> 0.811 | Improved |
| use PT instead of multi-scale pooling (ablation) | UGTR · COD10K-Test | S-measure: 0.792 -> 0.811 | Improved |
| add LPL loss to UGT + PT (ablation) | UGTR · COD10K-Test | S-measure: 0.811 -> 0.818 | Improved |
| add uncertainty-guided random masking (UGRM) vs no masking (ablation) | UGTR · COD10K-Test | S-measure: 0.797 -> 0.818 | Improved |
| use UGRM instead of standard random masking (ablation) | UGTR · CAMO-Test | S-measure: 0.775 -> 0.785 | Improved |
| increase number of prototypes T from 8 to 16 (ablation) | UGTR · COD10K-Test | S-measure: 0.806 -> 0.818 | Improved |
| increase number of prototypes T from 16 to 32 (ablation) | UGTR · COD10K-Test | S-measure: 0.818 -> 0.817 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EGNet — EGNet: Edge Guidance Network for Salient Object Detection (ICCV 2019) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PASR: Pattern-Aware Scene-Conditioned Reasoning for Camouflaged Object Detection (ECCV 2026 · similarity 0.90)
- Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection (CVPR 2021 · similarity 0.87)
- Conditional Diffusion Models for Camouflaged and Salient Object Detection (TPAMI 2025 · similarity 0.87)
- Uncertainty Quantification in Detection Transformers: Object-Level Calibration and Image-Level Reliability (TPAMI 2026 · similarity 0.87)
- CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models (AAAI 2024 · similarity 0.86)
- Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion (ICLR 2025 · 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.
