Research map / Label-efficient and robust learning / Domain adaptation and generalization
Energy-guided Dual Domain-invariant Prompting Framework with Fourier Regularization for Generalized Few-Shot Medical Segmentation
Shaolei Liu, Yuting Wu, Dongchen Zhu, Jiamao Li
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 EMME multi-band momentum augmentation (ablation) | baseline · Prostate (25% labels) | average score: 70.65 -> 71.75 | Improved |
| add frequency prompt to EMME (ablation) | baseline + EMME · Prostate (25% labels) | average score: 71.75 -> 73.12 | Improved |
| add text prompt to EMME (ablation) | baseline + EMME · Prostate (25% labels) | average score: 71.75 -> 72.57 | Improved |
| add frequency consistency regularization (FCR) (ablation) | baseline with prompts · Prostate (25% labels) | average score: 73.76 | Improved |
| combine all components (ablation) | DIPO · Prostate (25% labels) | average score: 70.65 -> 75.84 | Improved |
| add EMME and FCR to DAPSAM (ablation) | DAPSAM · Prostate (25% labels) | average score: 72.83 -> 73.68 | Improved |
| add EMME and FCR to Med-SA (ablation) | Med-SA · Prostate (25% labels) | average score: 71.78 -> 72.94 | Improved |
| set NSST decomposition levels to 3 (ablation) | DIPO · Prostate and OD/OC | segmentation performance | Improved |
| set band division radii R1=4, R2=2 (ablation) | DIPO · Prostate and OD/OC | segmentation performance | Improved |
| use DIPO instead of DAPSAM | DAPSAM · OD/OC (25% labels) | average score: 80.65 -> 82.48 | Improved |
Closest papers by meaning
- LangDAug: Langevin Data Augmentation for Multi-Source Domain Generalization in Medical Image Segmentation (ICML 2025 · similarity 0.88)
- Learning Generalized Medical Image Segmentation from Decoupled Feature Queries (AAAI 2024 · similarity 0.87)
- Why Invariance is Not Enough for Biomedical Domain Generalization and How to Fix It (NeurIPS 2026 · similarity 0.87)
- FAMNet: Frequency-aware Matching Network for Cross-domain Few-shot Medical Image Segmentation (AAAI 2025 · similarity 0.86)
- Modality-agnostic Domain Generalizable Medical Image Segmentation by Multi-Frequency in Multi-Scale Attention (CVPR 2024 · similarity 0.86)
- beta-FFT: Nonlinear Interpolation and Differentiated Training Strategies for Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.86)
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.
