Research map / Vision-language and multimodal / CLIP and zero-shot
Simple-ViLMedSAM: Simple Text Prompts Meet Vision-Language Models for Medical Image Segmentation
Chengcan Qian, Dong Nie, Geng Chen, Daoqiang Zhang, Xuyun Wen
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 Implicit Pos-Prompter to baseline (ablation) | Simple-ViLMedSAM · Kvasir-SEG (zero-shot) | Dice (%): 46.69 -> 52.74 | Improved |
| add Bidirectional Interaction Decoder alone to baseline (ablation) | Simple-ViLMedSAM · Kvasir-SEG (zero-shot) | Dice (%): 46.69 -> 54.47 | Improved |
| combine IPP and BID (ablation) | Simple-ViLMedSAM · Kvasir-SEG (zero-shot) | Dice (%): 46.69 -> 55.02 | Improved |
| enable LoRA adapters on SAM encoder (ablation) | Simple-ViLMedSAM · Kvasir-SEG (zero-shot) | Dice (%): 55.02 -> 59.83 | Improved |
| add BID on top of LoRA + IPP (ablation) | Simple-ViLMedSAM · Kvasir-SEG (zero-shot) | Dice (%): 59.02 -> 59.83 | Improved |
| use complex clinical text instead of simple text prompts (ablation) | SaLIP · Zero-shot, four datasets | Dice (%): +4.85 | Improved |
| use complex clinical text instead of simple text prompts (ablation) | MedCLIP-SAM v2 · Zero-shot, four datasets | Dice (%): +10.86 | Improved |
| use complex clinical text instead of simple text prompts (ablation) | Simple-ViLMedSAM · Zero-shot, four datasets | Dice (%): +0.71 | No clear effect |
| implicit positional prompts with simple text vs best baseline on Chest CT | Simple-ViLMedSAM · Chest CT (zero-shot) | Dice (%): +7.35 | Improved |
| few-shot adaptation of Simple-ViLMedSAM vs H-SAM on Chest X-ray | Simple-ViLMedSAM · Chest X-ray (few-shot) | Dice (%): 90.00 -> 90.34 | Improved |
Closest papers by meaning
- MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation (CVPR 2026 · similarity 0.90)
- CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation (NeurIPS 2024 · similarity 0.89)
- Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.89)
- One-Prompt to Segment All Medical Images (CVPR 2024 · similarity 0.88)
- BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models (CVPR 2025 · similarity 0.87)
- RADAR: Text-Guided Medical Image Segmentation via Residual Aggregation and Dense Alignment Representations (NeurIPS 2026 · 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.
