Research map / Detection and segmentation / Open-set and few-shot detection
Feature Weighting and Boosting for Few-Shot Segmentation
Khoi Nguyen, Sinisa Todorovic
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 feature weighting (contribution 1) (ablation) | B, VGG 16 · PASCAL-5i one-shot | mIoU: 47.55 -> 48.68 | Improved |
| add feature weighting (contribution 1) (ablation) | B, ResNet 101 · PASCAL-5i one-shot | mIoU: 51.30 -> 52.71 | Improved |
| add feature boosting with an ensemble of experts (contribution 2) (ablation) | B, VGG 16 · PASCAL-5i one-shot | mIoU: 47.55 -> 51.22 | Improved |
| add feature boosting with an ensemble of experts (contribution 2) (ablation) | B, ResNet 101 · PASCAL-5i one-shot | mIoU: 51.30 -> 54.21 | Improved |
| add feature weighting (contribution 1) (ablation) | B+C2, VGG 16 · PASCAL-5i one-shot | mIoU: 51.22 -> 51.90 | Improved |
| add feature weighting (contribution 1) (ablation) | B+C2, ResNet 101 · PASCAL-5i one-shot | mIoU: 54.21 -> 56.19 | Improved |
| add feature weighting (contribution 1) (ablation) | B, VGG 16 · COCO-20i one-shot | mIoU: 13.26 -> 17.11 | Improved |
| add feature weighting (contribution 1) (ablation) | B, ResNet 101 · COCO-20i one-shot | mIoU: 17.23 -> 18.86 | Improved |
| add feature boosting with an ensemble of experts (contribution 2) (ablation) | B, VGG 16 · COCO-20i one-shot | mIoU: 13.26 -> 17.73 | Improved |
| add feature boosting with an ensemble of experts (contribution 2) (ablation) | B, ResNet 101 · COCO-20i one-shot | mIoU: 17.23 -> 19.56 | Improved |
| jointly analyze K support images instead of averaging per-support predictions (ablation) | B+C1+C2, VGG 16 · PASCAL-5i five-shot | mIoU: 52.62 -> 55.08 | Improved |
| jointly analyze K support images instead of averaging per-support predictions (ablation) | B+C1+C2, ResNet 101 · PASCAL-5i five-shot | mIoU: 57.78 -> 59.92 | Improved |
Closest papers by meaning
- Simpler Is Better: Few-Shot Semantic Segmentation With Classifier Weight Transformer (ICCV 2021 · similarity 0.91)
- Learning What Not To Segment: A New Perspective on Few-Shot Segmentation (CVPR 2022 · similarity 0.89)
- Holistic Prototype Activation for Few-Shot Segmentation (TPAMI 2022 · similarity 0.89)
- Foreground-Covering Prototype Generation and Matching for SAM-Aided Few-Shot Segmentation (AAAI 2025 · similarity 0.88)
- 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 0.88)
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.
