Research map / Detection and segmentation / CNN features
Feature-Proxy Transformer for Few-Shot Segmentation
Jian-Wei Zhang, Yifan Sun, Yi Yang, Wei Chen
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 pairwise loss that pulls foreground features together (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: +1.1% PASCAL-5^i; +0.4% COCO-20^i | Improved |
| Add query-support prompting and interaction (ablation) | FPTrans with pairwise loss · PASCAL-5^i and COCO-20^i 1-shot | mIoU: +1.0% PASCAL-5^i; +2.7% COCO-20^i | Improved |
| Add multiple local background proxies (ablation) | FPTrans with pairwise loss · PASCAL-5^i and COCO-20^i 1-shot | mIoU: +1.1% PASCAL-5^i; +1.5% COCO-20^i | Improved |
| Use all three components: pairwise loss, prompts, and multiple local proxies (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: +2.9% PASCAL-5^i; 3.6% COCO-20^i | Improved |
| Use learnable prompts without extracted prompts (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: 64.0 -> 63.5; 40.3 -> 39.2 | Hurt |
| Add learnable vectors to extracted prompts (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: 64.3 -> 64.7; 41.4 -> 42.0 | Improved |
| Include background-background pairs in the pairwise loss (ablation) | FPTrans · PASCAL-5^i 1-shot | mIoU: 64.7 -> 64.0 (50%); 64.7 -> 63.8 (100%) | Hurt |
| Increase local background proxy count from 1 to 5 (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: 63.9 -> 64.7; 41.5 -> 42.0 | Improved |
| Increase local background proxy count from 5 to 9 (ablation) | FPTrans · PASCAL-5^i and COCO-20^i 1-shot | mIoU: 64.7 -> 64.0; 42.0 -> 41.2 | Hurt |
| Replace CNN backbones with transformer backbones in decoder-based methods (ablation) | PFENet and CyCTR · PASCAL-5^i 1-shot | mIoU: PFENet: 60.8 -> 58.7 (ViT), 57.7 (DeiT); CyCTR: 64.2 -> 60.1 (ViT), 61.0 (DeiT) | Hurt |
| Use FPTrans instead of HSNet under COCO-to-PASCAL domain shift | FPTrans · COCO-20^i→PASCAL-5^i 1-shot and 5-shot | mIoU: +5.6%; +9.0% | Improved |
Closest papers by meaning
- Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement (AAAI 2024 · similarity 0.90)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.89)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.89)
- DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation (CVPR 2025 · similarity 0.88)
- Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation (CVPR 2024 · similarity 0.88)
- Text Augmented Correlation Transformer For Few-shot Classification & Segmentation (CVPR 2025 · 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.
