AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

LIMITR: Leveraging Local Information for Medical Image-Text Representation

Gefen Dawidowicz, Elad Hirsch, Ayellet Tal

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 24 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 internal and external losses to global loss (ablation)LIMITR · MIMIC-CXR image-to-textR@1: 31.8 -> 36.1Improved
add global loss to local losses (ablation)LIMITR · MIMIC-CXR text-to-imageR@1: 31.5 -> 36.4Improved
add lateral images (ablation)LIMITR · MIMIC-CXR image-to-textR@1: 36.1 -> 38.1Improved
add positional encoding (ablation)LIMITR · MIMIC-CXR image-to-textR@1: 36.1 -> 37.7Improved
add positional encoding (frontal only) (ablation)LIMITR · MIMIC-CXR text-to-imageR@1: 36.4 -> 34.7Hurt
add both lateral images and positional encoding (ablation)LIMITR · MIMIC-CXR image-to-textR@1: 36.1 -> 39.7Improved
LIMITR vs GLoRIA on large-K class-based retrievalGLoRIA · CheXpert 5X200 zero-shotPrec@100: 29.0 -> 28.8No clear effect

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