AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Boosting Vision Semantic Density with Anatomy Normality Modeling for Medical Vision-language Pre-training

Weiwei Cao, Jianpeng Zhang, Zhongyi Shui, Sinuo Wang, Zeli Chen, Xi Li, Le Lu, Xianghua Ye, Qi Zhang, Tingbo Liang, Ling Zhang

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 8 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 anatomy-wise fine-grained image-report alignment (ViT encoder) (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 70.9 -> 76.5Improved
use a CNN instead of ViT as vision encoder (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 76.5 -> 78.7Improved
add instance-level contrastive learning for visual semantic enhancement (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 78.7 -> 79.7Improved
use disease-level rather than instance-level contrastive learning (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 79.7 -> 80.7Improved
add vision semantic density boosting (VQ-VAE normality modeling) (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 80.7 -> 82.5Improved
initialize encoder with disease-level contrastive pretraining instead of random (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 78.7 -> 80.7Improved
initialize encoder with disease-level contrastive pretraining instead of supervised classification (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 79.4 -> 80.7Improved
use larger ResNet34 or ResNet50 instead of ResNet18 (ablation)ViSD-Boost · MedVL-CT69K validation zero-shotAUC: 78.7 -> 79.0Improved
compare ViSD-Boost with base model on local diseasesViSD-Boost · MedVL-CT69K zero-shot, local diseasesAUC: 76.3 -> 80.3Improved
compare ViSD-Boost with base model on diffuse diseasesViSD-Boost · MedVL-CT69K zero-shot, diffuse diseasesAUC: 85.2 -> 88.0Improved
replace fVLM with ViSD-Boost on MedVL-CT69KViSD-Boost · MedVL-CT69K zero-shot (54 diseases, 15 organs)average AUC: 81.3 -> 84.9Improved
replace fVLM with ViSD-Boost on Rad-ChestCT precisionViSD-Boost · Rad-ChestCT zero-shot (external)precision: 37.4 -> 34.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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