Research map / Label-efficient and robust learning / Test-time adaptation
SPDA: Efficient Online Test-Time Adaptation for Promptable Medical Segmentation
Huixuan Xu, Hu Han, Shiguang Shan, Xilin CHEN
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 SPDA test-time adaptation | SAM2 · 11 modalities, box prompts | average DSC (%): 67.11 -> 74.18 | Improved |
| add SPDA test-time adaptation | SAM2 · 11 modalities, 3-click points | average DSC (%): 51.48 -> 61.44 | Improved |
| add SPDA test-time adaptation | MedSAM2 · 11 modalities, box prompts | average DSC (%): 83.36 -> 88.05 | Improved |
| add SPDA test-time adaptation | MedSAM2 · 11 modalities, points | average DSC (%): 78.02 -> 81.11 | Improved |
| add SPDA | SAM · other backbones | average DSC (%): 65.48 -> 70.16 | Improved |
| add SPDA | MedSAM · other backbones | average DSC (%): 71.64 -> 72.82 | Improved |
| add low-frequency radial-spectrum input perturbation (ablation) | SPDA · MedSAM2 box ablation subset | average DSC (%): 80.07 -> 83.91 | Improved |
| add prompt under-sampling perturbation alone (ablation) | SPDA · MedSAM2 box ablation subset | average DSC (%): 80.07 -> 81.45 | Improved |
| add prompt under-sampling on top of input perturbation (ablation) | SPDA · MedSAM2 box ablation subset | average DSC (%): 83.91 -> 85.04 | Improved |
| replace traditional augmentations with our input perturbation (ablation) | SPDA with prompt perturbation · MedSAM2 box ablation subset | average DSC (%): 83.78 -> 85.04 | Improved |
| use post-encoder adapter instead of LoRA (ablation) | SPDA · MedSAM2 box ablation subset | average DSC (%) and TFLOPs: 85.11 -> 85.04; 78.90 -> 39.88 TFLOPs | No clear effect |
| use post-encoder adapter instead of LN optimization (ablation) | SPDA · MedSAM2 box ablation subset | average DSC (%): 80.85 -> 85.04 | Improved |
Closest papers by meaning
- Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation (CVPR 2024 · similarity 0.91)
- Efficient Deformable Convolutional Prompt for Continual Test-Time Adaptation in Medical Image Segmentation (AAAI 2025 · similarity 0.91)
- Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation (AAAI 2025 · similarity 0.89)
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.86)
- Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding (CVPR 2024 · similarity 0.86)
- AIF-SFDA: Autonomous Information Filter Driven Source-Free Domain Adaptation for Medical Image Segmentation (AAAI 2025 · similarity 0.85)
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.
