AI Paper Atlas

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

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add semantic anchor loss L_anc (ablation)vMFCoOp base · Base-to-novelHarmonic mean: 52.14 -> 70.98Improved
add semantic anchor loss L_anc to symmetric cross-entropy (ablation)vMFCoOp · Base-to-novelHarmonic mean: 56.39 -> 74.71Improved
add semantic anchor loss L_anc (ablation)vMFCoOp base · Few-shot 16-shotaccuracy: 60.90 -> 63.87Improved
add spherical contrastive loss L_sc to L_anc (ablation)vMFCoOp · Base-to-novelHarmonic mean: 70.98 -> 73.42Improved
add spherical contrastive loss L_sc to L_anc (ablation)vMFCoOp · Few-shot 16-shotaccuracy: 63.87 -> 73.25Improved
add spherical contrastive loss L_sc to L_SCE + L_anc (ablation)vMFCoOp · Base-to-novelHarmonic mean: 74.71 -> 77.15Improved
add spherical contrastive loss L_sc to L_SCE + L_anc (ablation)vMFCoOp · Few-shot 1-shotaccuracy: 54.88 -> 57.25Improved
add symmetric cross-entropy L_SCE to L_anc + L_sc (ablation)vMFCoOp · Base-to-novelHarmonic mean: 73.42 -> 77.15Improved
add symmetric cross-entropy L_SCE to L_anc + L_sc (ablation)vMFCoOp · Few-shot 1-shotaccuracy: 49.87 -> 57.25Improved
add symmetric cross-entropy alone to the base prompt learner (ablation)vMFCoOp base · Base-to-novelHarmonic mean: 52.14 -> 56.39Improved
add L_sc to L_anc in 1-shot (ablation)vMFCoOp · Few-shot 1-shotaccuracy: 50.29 -> 49.87No clear effect
use vMFCoOp instead of BiomedCoOpBiomedCLIP prompt learning · 14 biomedical datasets, 4-shotaverage accuracy: 63.65 -> 68.29Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy