Research map / Detection and segmentation / Open-set and few-shot detection
Simpler Is Better: Few-Shot Semantic Segmentation With Classifier Weight Transformer
Zhihe Lu, Sen He, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang
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 |
|---|---|---|---|
| meta-train the classifier only instead of the whole model (ablation) | CWT · COCO-20i 1-shot (ResNet-50) | mIoU (%): 21.5 -> 32.9 | Improved |
| add CWT classifier adaptation to each query image on top of pre-trained classifier (ablation) | CWT · COCO-20i 1-shot (ResNet-50) | mIoU (%): 28.6 -> 32.9 | Improved |
| condition CWT on the query image instead of the support image (ablation) | CWT · COCO-20i 1-shot (ResNet-50) | mIoU (%): 18.2 -> 32.9 | Improved |
| pre-train encoder/decoder and train classifier on support only (no meta-learning) vs PPNet (ablation) | pre-training baseline · COCO-20i 1-shot (ResNet-50) | mIoU (%): 25.7 -> 28.6 | Improved |
| use CWT vs best competitor with ResNet-50 | CWT · COCO-20i 1-shot | mIoU (%): 30.6 -> 32.9 | Improved |
| use CWT vs PPNet in 5-shot with ResNet-50 | CWT · COCO-20i 5-shot | mIoU (%): 36.2 -> 41.3 | Improved |
| use CWT vs PFENet in 5-shot with ResNet-101 | CWT · COCO-20i 5-shot | mIoU (%): 37.4 -> 42.0 | Improved |
| use CWT vs PFENet in 1-shot | CWT · PASCAL-5i 1-shot (ResNet-50) | mIoU (%): 60.8 -> 56.4 | Hurt |
| use CWT vs PFENet in 5-shot | CWT · PASCAL-5i 5-shot (ResNet-50) | mIoU (%): 61.9 -> 63.7 | Improved |
| use CWT vs RPMMs in COCO to PASCAL transfer | CWT · COCO to PASCAL 1-shot | mIoU (%): 49.6 -> 59.5 | Improved |
| use CWT vs RPMMs in PASCAL to COCO transfer | CWT · PASCAL to COCO 5-shot | mIoU (%): 41.0 -> 45.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 2 of 2 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
- Learning Meta-Class Memory for Few-Shot Semantic Segmentation (ICCV 2021 · similarity 0.91)
- Cross-Domain Few-Shot Semantic Segmentation (ECCV 2022 · similarity 0.91)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.91)
- Feature Weighting and Boosting for Few-Shot Segmentation (ICCV 2019 · similarity 0.91)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.91)
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 2024 · similarity 0.89)
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.
