Research map / Detection and segmentation / Open-set and few-shot detection
Integrative Few-Shot Learning for Classification and 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 |
|---|---|---|---|
| Use ASNet rather than HSNet under the iFSL framework | FS-CS · Pascal-5ᶦ, 1-way 1-shot | classification 0/1 exact ratio (%): 83.7 -> 84.9 | Helped |
| Use ASNet rather than HSNet under the iFSL framework | FS-CS · Pascal-5ᶦ, 1-way 1-shot | segmentation mIoU (%): 49.7 -> 52.3 | Helped |
| Use ASNet rather than HSNet | FS-CS · COCO-20ᶦ, 1-way 1-shot | mIoU: 34.3 -> 35.8 | Helped |
| Replace global self-attention with local self-attention (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | segmentation mIoU: 52.3 -> 44.6 | Hurt |
| Remove attention masking (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | segmentation mIoU: 52.3 -> 50.8 | Hurt |
| Replace multi-layer fusion with support-dimension average pooling and element-wise addition (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | classification ER: 84.9 -> 83.1 | Hurt |
| Replace multi-layer fusion with support-dimension average pooling and element-wise addition (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | segmentation mIoU: 52.3 -> 51.6 | Hurt |
| Train with class-tag classification loss only rather than segmentation annotations (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | segmentation mIoU: 52.3 -> 15.0 | Hurt |
| Add classification loss to segmentation loss (ablation) | ASNet · Pascal-5ᶦ FS-CS, 1-way 1-shot | segmentation mIoU: 52.3 -> 52.1 | No clear effect |
Closest papers by meaning
- Text Augmented Correlation Transformer For Few-shot Classification & Segmentation (CVPR 2025 · similarity 0.89)
- Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement (AAAI 2024 · similarity 0.89)
- Pushing the Limit of Fine-Tuning for Few-Shot Learning: Where Feature Reusing Meets Cross-Scale Attention (AAAI 2024 · similarity 0.89)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.88)
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 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)
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.