Research map / Detection and segmentation / Open-set and few-shot detection
Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation
Tianyu Zou, Shengwu Xiong, Ruilin Yao, Yi Rong
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 PFE module (ablation) | SCCAN baseline · PASCAL-5i (1-shot, SCCAN+BAM baseline, module ablation) | mean mIoU: 68.4 -> 70.3 | Improved |
| add ASC module (ablation) | SCCAN baseline · PASCAL-5i (1-shot, SCCAN+BAM baseline, module ablation) | mean mIoU: 68.4 -> 71.0 | Improved |
| add ASC module on top of PFE (ablation) | PFE variant · PASCAL-5i (1-shot, SCCAN+BAM baseline, module ablation) | mean mIoU: 70.3 -> 71.6 | Improved |
| add PFE module on top of ASC (ablation) | ASC variant · PASCAL-5i (1-shot, SCCAN+BAM baseline, module ablation) | mean mIoU: 71.0 -> 71.6 | Improved |
| use SSP prototype predictor instead of SCCAN affinity model as predictor (ablation) | HDMNet+PAHNet · PASCAL-5i (1-shot, prototype predictor ablation) | mean mIoU: 70.4 -> 71.5 | Improved |
| add PAHNet to HDMNet | HDMNet · PASCAL-5i (1-shot) | mean mIoU: 69.4 -> 71.5 | Improved |
| add PAHNet to HDMNet | HDMNet · PASCAL-5i (5-shot) | mean mIoU: 71.8 -> 76.1 | Improved |
| add PAHNet to SCCAN | SCCAN · PASCAL-5i (1-shot) | mean mIoU: 66.8 -> 71.6 | Improved |
| add PAHNet to SCCAN | SCCAN · PASCAL-5i (5-shot) | mean mIoU: 70.3 -> 75.3 | Improved |
| add PAHNet to SCCAN | SCCAN · COCO-20i (1-shot) | mean mIoU: 46.3 -> 50.2 | Improved |
| add PAHNet to SCCAN | SCCAN · COCO-20i (5-shot) | mean mIoU: 53.9 -> 57.5 | Improved |
| add PAHNet to HDMNet | HDMNet · COCO-20i (1-shot) | mean mIoU: 49.6 -> 52.3 | Improved |
Closest papers by meaning
- Training-free Boosting for Few-shot Segmentation via Generalizing Semantic Mining (AAAI 2026 · similarity 0.90)
- Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation (AAAI 2025 · similarity 0.90)
- Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement (AAAI 2024 · similarity 0.90)
- Mining Latent Classes for Few-Shot Segmentation (ICCV 2021 · similarity 0.90)
- Task-Disruptive Background Suppression for Few-Shot Segmentation (AAAI 2024 · similarity 0.89)
- Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation (CVPR 2024 · similarity 0.88)
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.
