Research map / Detection and segmentation / Open-set and few-shot detection
Learning from the Target: Dual Prototype Network 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 |
|---|---|---|---|
| Add the dual-prototype modules to PFENet | PFENet · PASCAL-5i 1-shot | mIoU: 60.8 -> 62.7 | Helped |
| Add the dual-prototype modules to PFENet | PFENet · PASCAL-5i 5-shot | mIoU: 61.9 -> 66.2 | Helped |
| Use DPNet instead of the strongest listed baseline | PASCAL-5i · PASCAL-5i 1-shot | mIoU: 59.7 -> 62.7 | Helped |
| Use DPNet instead of the strongest listed baseline | PASCAL-5i · PASCAL-5i 5-shot | mIoU: 66.6 -> 66.2 | Hurt |
| Use DPNet instead of the strongest listed baseline | COCO-20i · COCO-20i 1-shot | mIoU: 37.0 -> 37.2 | Helped |
| Use DPNet instead of the strongest listed baseline | COCO-20i · COCO-20i 5-shot | mIoU: 42.5 -> 42.9 | Helped |
| Add PIM to the baseline network (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 53.8 -> 55.5 | Helped |
| Add MSF after PIM (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 55.5 -> 56.0 | Helped |
| Add CCM to the PIM and MSF network (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 56.0 -> 58.0 | Helped |
| Replace cycle-consistent foreground selection with global query-image average features (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 58.0 -> 56.5 | Hurt |
| Replace cycle-consistent foreground selection with cosine-similarity selection (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 58.0 -> 57.3 | Hurt |
| Use multi-scale inference (ablation) | DPNet · PASCAL-5i 1-shot | mIoU: 58.0 -> 58.7 | Helped |
Closest papers by meaning
- Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation (AAAI 2025 · similarity 0.89)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.88)
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 2024 · similarity 0.87)
- Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation (AAAI 2024 · similarity 0.87)
- Task-Disruptive Background Suppression for Few-Shot Segmentation (AAAI 2024 · similarity 0.87)
- Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation (NeurIPS 2024 · 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.