AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Towards Unifying Medical Vision-and-Language Pre-Training via Soft Prompts

Zhihong Chen, Shizhe Diao, Benyou Wang, Guanbin Li, Xiang Wan

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 45 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 ITC objective to MLM+ITM pre-training (ablation)PTUnifier · CheXpert 1% dataAUROC: 74.5 -> 88.7Improved
add ITC objective to MLM+ITM pre-training (ablation)PTUnifier · RadNLI text classificationaccuracy: 78.3 -> 80.0Improved
use ITC only instead of MLM+ITM+ITC for text classification (ablation)PTUnifier · RadNLI text classificationaccuracy: 78.3 -> 76.5Hurt
add MLM and ITM fusion objectives to ITC (ablation)PTUnifier · VQA-RAD overallaccuracy: 74.6 -> 78.3Improved
add ITM to MLM (ablation)PTUnifier · VQA-RAD overallaccuracy: 70.8 -> 77.7Improved
add MLM and ITM to ITC on image-to-text generation (ablation)PTUnifier · MIMIC-CXR image-to-text generationBLEU-4: 10.3 -> 10.7Improved
unify Med-VLP with visual and textual prompt pools versus task-specific state-of-the-artPTUnifier · ROCO image-to-text retrievalRecall@1: 14.5 -> 21.0Improved
unify Med-VLP with prompt pools versus task-specific state-of-the-art on image generationPTUnifier · MIMIC-CXR image-to-text generationBLEU-4: 10.5 -> 10.7Improved
unify Med-VLP with prompt pools versus task-specific state-of-the-art on VQAPTUnifier · VQA-RADaccuracy: 72.7 -> 78.3Improved

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