Research map / Vision-language and multimodal / CLIP and zero-shot
vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs
Minye Shao, Sihan Guo, Xinrun Li, Xingyu Miao, Haoran Duan, Yang Long
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 semantic anchor loss L_anc (ablation) | vMFCoOp base · Base-to-novel | Harmonic mean: 52.14 -> 70.98 | Improved |
| add semantic anchor loss L_anc to symmetric cross-entropy (ablation) | vMFCoOp · Base-to-novel | Harmonic mean: 56.39 -> 74.71 | Improved |
| add semantic anchor loss L_anc (ablation) | vMFCoOp base · Few-shot 16-shot | accuracy: 60.90 -> 63.87 | Improved |
| add spherical contrastive loss L_sc to L_anc (ablation) | vMFCoOp · Base-to-novel | Harmonic mean: 70.98 -> 73.42 | Improved |
| add spherical contrastive loss L_sc to L_anc (ablation) | vMFCoOp · Few-shot 16-shot | accuracy: 63.87 -> 73.25 | Improved |
| add spherical contrastive loss L_sc to L_SCE + L_anc (ablation) | vMFCoOp · Base-to-novel | Harmonic mean: 74.71 -> 77.15 | Improved |
| add spherical contrastive loss L_sc to L_SCE + L_anc (ablation) | vMFCoOp · Few-shot 1-shot | accuracy: 54.88 -> 57.25 | Improved |
| add symmetric cross-entropy L_SCE to L_anc + L_sc (ablation) | vMFCoOp · Base-to-novel | Harmonic mean: 73.42 -> 77.15 | Improved |
| add symmetric cross-entropy L_SCE to L_anc + L_sc (ablation) | vMFCoOp · Few-shot 1-shot | accuracy: 49.87 -> 57.25 | Improved |
| add symmetric cross-entropy alone to the base prompt learner (ablation) | vMFCoOp base · Base-to-novel | Harmonic mean: 52.14 -> 56.39 | Improved |
| add L_sc to L_anc in 1-shot (ablation) | vMFCoOp · Few-shot 1-shot | accuracy: 50.29 -> 49.87 | No clear effect |
| use vMFCoOp instead of BiomedCoOp | BiomedCLIP prompt learning · 14 biomedical datasets, 4-shot | average accuracy: 63.65 -> 68.29 | Improved |
Closest papers by meaning
- BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models (CVPR 2025 · similarity 0.91)
- LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding (CVPR 2026 · similarity 0.88)
- How Do Medical MLLMs Fail? A Study on Visual Grounding in Medical Images (ICLR 2026 · similarity 0.87)
- ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization (ICML 2025 · similarity 0.87)
- Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE (NeurIPS 2024 · 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.
