AI Paper Atlas

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

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

Pujin Cheng, Li Lin, Junyan Lyu, Yijin Huang, Wenhan Luo, Xiaoying Tang

ICCV 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 95 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 local alignment module to global alignment (ablation)PRIOR · SIIM classification 1% labeledAUC-ROC (%): 82.01 -> 84.86Improved
add cross-modality conditional reconstruction (ablation)PRIOR · SIIM classification 1% labeledAUC-ROC (%): 84.86 -> 85.80Improved
add sentence prototype memory bank to LAM+CCR (ablation)PRIOR · SIIM classification 1% labeledAUC-ROC (%): 85.80 -> 87.27Improved
add sentence prototype memory bank to LAM without CCR (ablation)PRIOR · SIIM classification 1% labeledAUC-ROC (%): 84.86 -> 86.81Improved
add all components on 1% SIIM segmentation (ablation)PRIOR · SIIM segmentation 1% labeledDice: 17.88 -> 20.43Improved
use PRIOR instead of MGCA on RSNA classificationclassification · RSNA classificationAUC-ROC (%): 89.30 -> 89.22 (100%)No clear effect
use PRIOR instead of MGCA on SIIM 10% classificationclassification · SIIM classification 10% labeledAUC-ROC (%): 89.68 -> 89.13Hurt
use PRIOR for zero-shot classification instead of GLoRIAzero-shot · CheXpert zero-shot 5x200accuracy (%): 23.20 -> 34.90Improved
use PRIOR for image-to-text retrieval instead of GLoRIAretrieval · CheXpert image-to-text retrieval 5x200Precision@1 (%): 29.3 -> 40.2Improved
use medical report pretraining for 1% RSNA detectiondetection · RSNA detection 1% labeledmAP(0.5:0.95): 0.20 vs below 0.1 for most methodsNo clear effect
use report-based VLP pretraining versus SSL for RSNA detectiondetection · RSNA detectionmAP(0.5:0.95)Mixed
fine-tune more ResNet blocks beyond linear evaluationevaluation protocol · CheXpert 1%AUC-ROCImproved

Later papers that compared with this method

2 later accepted papers report PRIOR as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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