Research map / Detection and segmentation / Open-set and few-shot detection
CRNet: Cross-Reference Networks for Few-Shot Segmentation
Check 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 cross-reference module to the condition-only model (ablation) | CRNet · PASCAL VOC 2012, 1-shot | mIoU: 36.3 -> 49.1 | Helped |
| Add the condition module to the cross-reference-only model (ablation) | CRNet · PASCAL VOC 2012, 1-shot | mIoU: 43.3 -> 49.1 | Helped |
| Add multi-scale input testing (ablation) | CRNet · PASCAL VOC 2012, 1-shot | mIoU: 49.1 -> 50.3 | Helped |
| Add mask refinement to the multi-scale model (ablation) | CRNet · PASCAL VOC 2012, 1-shot | mIoU: 50.3 -> 53.4 | Helped |
| Add multi-level features to the model with mask refinement and multi-scale testing (ablation) | CRNet · PASCAL VOC 2012, 1-shot | mIoU: 53.4 -> 55.2 | Helped |
| Add finetuning on the support examples rather than using fusion | CRNet · PASCAL VOC 2012, 5-shot | mIoU: 50.2 -> 57.5 | Helped |
| Increase support examples from 5-shot to 10-shot with finetuning | CRNet · PASCAL VOC 2012, 5-shot vs 10-shot | mIoU: 57.5 -> 59.1 | Helped |
| Increase support examples from 5-shot to 10-shot with fusion | CRNet · PASCAL VOC 2012, 5-shot vs 10-shot | mIoU: 50.2 -> 49.9 | Hurt |
| Add the mask-refine module (ablation) | CRNet · MS COCO, 1-shot | mIoU: 44.9 -> 45.8 | Helped |
| Add the mask-refine module (ablation) | CRNet · MS COCO, 5-shot | mIoU: 45.6 -> 47.2 | Helped |
Closest papers by meaning
- Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer (CVPR 2022 · similarity 0.89)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.88)
- Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation (CVPR 2024 · similarity 0.87)
- The Devil is in Low-Level Features for Cross-Domain Few-Shot Segmentation (CVPR 2025 · similarity 0.87)
- Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation (NeurIPS 2024 · similarity 0.87)
- A Surprisingly Simple Approach to Generalized 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.