AI Paper Atlas

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

Joint Learning of Localized Representations from Medical Images and Reports

Philip Müller, Georgios Kaissis, Congyu Zou, Daniel Rueckert

ECCV 2022 · 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 (region and sentence) weighting (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 16.9 -> 17.9Improved
add attention pooling instead of avg/max pooling (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 15.7 -> 16.9Improved
add global loss to local-only model (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 12.3 -> 15.7Improved
use smooth positiveness in local image loss (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 15.6 -> 17.9Improved
add local report loss to global plus local image loss (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 13.7 -> 17.9Improved
add local image loss to global plus local report loss (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 16.2 -> 17.9Improved
add local losses to global-loss model with attention pooling (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 17.4 -> 17.9Improved
add local losses to global-loss model with avg/max pooling (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 14.2 -> 15.7Improved
use attention pooling with only global loss (ablation)LoVT · RSNA YOLOv3 Frozen 10% (ablation, pre-train 30%)mAP (%): 14.2 -> 17.4Improved
use LoVT instead of ConVIRTLoVT · RSNA YOLOv3 Frozen 10% (pre-train 30% MIMIC-CXR)mAP (%): 14.8 -> 17.9Improved
pre-train on 100% instead of 30% of MIMIC-CXRLoVT · RSNA YOLOv3 Frozen 10%mAP (%): 17.9 -> 16.4Mixed
use LoVT instead of ConVIRT on NIH CXRLoVT · NIH CXR Linear (pre-train 100%)Avg Dice (%): 18.6 -> 9.4Hurt

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