Research map / Detection and segmentation / Open-set and few-shot detection
Few-Shot Semantic Segmentation with Democratic Attention Networks
Haochen Wang, Xudong Zhang, Yutao Hu, Yandan Yang, Xianbin Cao, Xiantong Zhen
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 democratized graph attention instead of regular graph attention, 0.8 support occlusion (1-shot) (ablation) | DAN · PASCAL-5i 1-shot | mean IoU (%): 41.7 -> 49.9 | Improved |
| Add democratized graph attention instead of regular graph attention, no occlusion (1-shot) (ablation) | DAN · PASCAL-5i 1-shot | mean IoU (%): 56.6 -> 58.1 | Improved |
| Add multi-scale inference (ablation) | DAN · PASCAL-5i 1-shot | mean IoU (%): 57.5 -> 58.2 | Improved |
| Add multi-scale inference (ablation) | DAN · PASCAL-5i 5-shot | mean IoU (%): 60.1 -> 60.5 | Improved |
| Add multi-level guidance (all three levels vs one level) (ablation) | DAN · PASCAL-5i 1-shot | mean IoU (%): 56.4 -> 58.2 | Improved |
| Add multi-level guidance (all three levels vs one level) (ablation) | DAN · PASCAL-5i 5-shot | mean IoU (%): 59.2 -> 60.5 | Improved |
| Use ResNet-101 instead of ResNet-50 backbone | DAN · PASCAL-5i 1-shot | mean IoU (%): 57.1 -> 58.2 | Improved |
| Use ResNet-101 instead of ResNet-50 backbone | DAN · PASCAL-5i 5-shot | mean IoU (%): 59.5 -> 60.5 | Improved |
| Use DAN instead of PANet on COCO-20i 5-shot | DAN · COCO-20i 5-shot | mean IoU (%): 29.7 -> 29.6 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 6 of 7 shared results
- CANet — CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning (CVPR 2019) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.90)
- Cross-Domain Few-Shot Semantic Segmentation (ECCV 2022 · similarity 0.90)
- Part-aware Prototype Network for Few-shot Semantic Segmentation (ECCV 2020 · similarity 0.89)
- Learning from the Target: Dual Prototype Network for Few Shot Semantic Segmentation (AAAI 2022 · similarity 0.89)
- Integrative Few-Shot Learning for Classification and Segmentation (CVPR 2022 · similarity 0.89)
- Unleashing the Potential of the Diffusion Model in 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.
