Research map / Detection and segmentation / Open-set and few-shot detection
Few-Shot Semantic Segmentation With Cyclic Memory Network
Guo-Sen Xie, Huan Xiong, Jie Liu, Yazhou Yao, Ling Shao
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 cyclic memory reading to multi-resolution baseline (ablation) | Baseline · PASCAL-5i (4-fold mean) | mean-IoU 1-shot: 59.9 -> 62.8 | Improved |
| add cyclic memory reading to multi-resolution baseline (ablation) | Baseline · COCO-20i (4-fold mean) | mean-IoU 1-shot: 36.0 -> 39.3 | Improved |
| add cyclic memory reading to multi-resolution baseline (ablation) | Baseline · COCO-20i (4-fold mean) | mean-IoU 5-shot: 39.7 -> 43.1 | Improved |
| add cyclic memory reading to multi-resolution baseline | Baseline · PASCAL-5i (4-fold mean) | FB-IoU 1-shot: 73.3 -> 72.3 | Hurt |
| add query feature re-adding (memory plus query value) (ablation) | CMN w Memory Value · PASCAL-5i (folds 0-1, ablation) | mean-IoU 5-shot: 66.7 -> 68.1 | Improved |
| add query feature re-adding (memory plus query value) (ablation) | CMN w Query Value · PASCAL-5i (folds 0-1, ablation) | mean-IoU 1-shot: 66.3 -> 67.2 | Improved |
| use ConvGRU recursive updating instead of concatenation (ablation) | CMN w Concatenate · PASCAL-5i (folds 0-1, ablation) | mean-IoU 1-shot: 65.8 -> 67.2 | Improved |
| use ConvGRU recursive updating instead of channel compression (ablation) | CMN w Compress · PASCAL-5i (folds 0-1, ablation) | mean-IoU 5-shot: 66.4 -> 68.1 | Improved |
| use three feature resolutions instead of two (ablation) | CMN N=2 · PASCAL-5i (folds 0-1, ablation) | mean-IoU 1-shot: 66.0 -> 67.2 | Improved |
| use four feature resolutions instead of three (ablation) | CMN N=3 · PASCAL-5i (folds 0-1, ablation) | mean-IoU 5-shot: 68.1 -> 67.6 | Hurt |
| use early feature fusion instead of mask-average late fusion (ablation) | CMN 5-shot · PASCAL-5i (4-fold, 5-shot fusion) | mean-IoU: 63.3 -> 63.7 | Improved |
| use early feature fusion instead of mask-OR late fusion (ablation) | CMN 5-shot · PASCAL-5i (4-fold, 5-shot fusion) | mean-IoU: 62.9 -> 63.7 | Improved |
Closest papers by meaning
- Cross-Domain Few-Shot Semantic Segmentation (ECCV 2022 · similarity 0.90)
- Object-level Correlation for Few-Shot Segmentation (ICCV 2025 · similarity 0.90)
- Scale-Aware Graph Neural Network for Few-Shot Semantic Segmentation (CVPR 2021 · similarity 0.89)
- Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation (CVPR 2022 · similarity 0.89)
- 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 0.88)
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.
