Research map / Detection and segmentation / Open-set and few-shot detection
Self-Support Few-Shot Semantic Segmentation
Qi Fan, Wenjie Pei, Yu-Wing Tai, Chi-Keung Tang
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 self-support module (SSM) (ablation) | baseline · PASCAL-5i 5-shot, ResNet-50 | mIoU: 64.8 -> 67.3 | Improved |
| add self-support loss (SSL) (ablation) | baseline · PASCAL-5i 5-shot, ResNet-50 | mIoU: 64.8 -> 65.7 | Improved |
| add self-support loss to SSM (ablation) | SSM · PASCAL-5i 5-shot, ResNet-50 | mIoU: 67.3 -> 68.1 | Improved |
| add adaptive self-support background prototype (ASBP) (ablation) | SSM · PASCAL-5i 5-shot, ResNet-50 | mIoU: 67.3 -> 68.2 | Improved |
| combine SSM, SSL and ASBP (ablation) | baseline · PASCAL-5i 5-shot, ResNet-50 | mIoU: 64.8 -> 68.8 | Improved |
| add self-support foreground prototype (ablation) | SSM · PASCAL-5i 5-shot, ResNet-50 | mIoU: 66.5 -> 67.3 | Improved |
| add self-support background prototype (ablation) | SSM · PASCAL-5i 5-shot, ResNet-50 | mIoU: 65.6 -> 67.3 | Improved |
| add support background prototype (ablation) | SSM · PASCAL-5i 5-shot, ResNet-50 | mIoU: 67.2 -> 67.3 | No clear effect |
| add non-local self-attention module instead of SSM (ablation) | baseline · PASCAL-5i 5-shot, ResNet-50 | mIoU: 64.8 -> 62.1 | Hurt |
| add self-support refinement (repeat procedure) | SSP · PASCAL-5i 5-shot, ResNet-101 | mIoU: 72.5 -> 73.1 | Improved |
| switch backbone ResNet-50 to ResNet-101 | SSP · PASCAL-5i 5-shot | mIoU: 68.8 -> 72.5 | Improved |
| add self-support module to PANet | PANet · PASCAL-5i | mIoU: 55.7 -> 58.3 | Improved |
Closest papers by meaning
- Learning from the Target: Dual Prototype Network for Few Shot Semantic Segmentation (AAAI 2022 · similarity 0.91)
- Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation (AAAI 2025 · similarity 0.89)
- Task-Disruptive Background Suppression for Few-Shot Segmentation (AAAI 2024 · similarity 0.88)
- Beyond Support Samples: Incorporating Unlabeled Queries for Few-Shot Semantic Segmentation (TPAMI 2026 · similarity 0.88)
- Bridge the Intra-Class Gap: K-Shot Multi-Scale Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation (TPAMI 2025 · similarity 0.88)
- Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation (CVPR 2024 · similarity 0.87)
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.
