Research map / Detection and segmentation / Open-set and few-shot detection
Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 intermediate prototype (support+query) instead of support-only prototype (ablation) | IPMT · PASCAL-5i 1-shot | mIoU: 62.5 -> 64.1 | Helped |
| use intermediate prototype instead of query-only prototype (ablation) | IPMT · PASCAL-5i 1-shot | mIoU: 59.8 -> 64.1 | Helped |
| add iteration to intermediate prototype mining (ablation) | IPMT · PASCAL-5i 1-shot | mIoU: 64.1 -> 66.8 | Helped |
| add iteration to support-only prototype (ablation) | Support-only prototype · PASCAL-5i 1-shot | mIoU: 62.5 -> 63.4 | Helped |
| add iteration to query-only prototype (ablation) | Query-only prototype · PASCAL-5i 1-shot | mIoU: 59.8 -> 60.1 | No clear effect |
| increase IPMT layers from 1 to 5 (ablation) | IPMT · PASCAL-5i 1-shot | mIoU: 64.1 -> 66.8 | Helped |
| add DSL to IPM (ablation) | IPMT · PASCAL-5i 1-shot | mIoU: 54.9 -> 64.3 | Helped |
| add query activation (QA) (ablation) | IPM + DSL · PASCAL-5i 1-shot | mIoU: 64.3 -> 66.8 | Helped |
| add IPM without DSL (ablation) | PA baseline · PASCAL-5i 1-shot | mIoU: 60.2 -> 54.9 | Hurt |
| IPMT vs best prior method with ResNet-50, 5-shot | IPMT · PASCAL-5i 5-shot | mIoU: 69.5 -> 68.2 | Hurt |
Closest papers by meaning
- Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining (CVPR 2024 · similarity 0.88)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.88)
- Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation (ICML 2024 · similarity 0.87)
- Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching (AAAI 2025 · similarity 0.86)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.86)
- Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation (AAAI 2025 · similarity 0.86)
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.