AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition

Shih-Cheng Huang, Liyue Shen, Matthew P. Lungren, Serena Yeung

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 545 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 representations to global at inference (ablation)GLoRIA · CheXpert 5x200 retrievalPrec@5: 67.02 -> 69.24Improved
add local representations to global at inference (ablation)GLoRIA · CheXpert 5x200 retrievalPrec@100: 49.55 -> 53.78Improved
add global representations to local only (ablation)GLoRIA · CheXpert 5x200 retrievalPrec@10: 64.58 -> 67.22Improved
add local contrastive loss to global-only contrastive training (vs ConVIRT) with global featuresGLoRIA · CheXpert 5x200 retrievalPrec@5: 66.98 -> 67.02No clear effect
use GLoRIA instead of ConVIRTGLoRIA · RSNA fine-tuned classification (1% labels)AUROC (%): 77.4 -> 86.1Improved
use GLoRIA instead of ConVIRTGLoRIA · CheXpert fine-tuned classification (1% labels)AUROC (%): 85.9 -> 86.6Improved
use GLoRIA 1% labels instead of ImageNet init with 100% labelsGLoRIA · CheXpert fine-tuned classificationAUROC (%): 81.4 -> 86.6Improved
use GLoRIA initialization instead of ConVIRTGLoRIA · SIIM pneumothorax segmentation (1% labels)Dice: 0.250 -> 0.358Improved
use GLoRIA initialization instead of ConVIRTGLoRIA · SIIM pneumothorax segmentation (10% labels)Dice: 0.432 -> 0.469Improved
use GLoRIA instead of ImageNet initialization with full labelsGLoRIA · SIIM pneumothorax segmentation (100% labels)Dice: 0.635 -> 0.634No clear effect
use zero-shot GLoRIA instead of fine-tuned classifier with 100% labelsGLoRIA · CheXpert 5x200 classificationF1: 0.63 -> 0.67Improved
use zero-shot GLoRIA instead of fine-tuning on 1% labelsGLoRIA · RSNA classificationF1: 0.57 -> 0.58No clear effect

Later papers that compared with this method

2 later accepted papers report GLoRIA as a baseline in their results tables; 1 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