Table 6 Comparison of CNR and mIoU for zero-shot phrase grounding on the MS-CXR datasets

From: Enhancing representation in radiography-reports foundation model: a granular alignment algorithm using masked contrastive learning

Method

Pretrained dataset

CNR

mIoU (%)

BioViL

PubMed + MIMIC-III + MIMIC-CXR

1.027

26.6

ConVIRT

MIMIC-CXR

0.818

23.8

GLoRIA

MIMIC-CXR

0.930

24.6

MaCo (Ours)

MIMIC-CXR

1.144

25.5

Back to article page