Self-supervised vision-language pretraining for Medical visual question answering

2 code implementations • 24 Nov 2022 • Pengfei Li, Gang Liu, Lin Tan, Jinying Liao, Shenjun Zhong

Medical image visual question answering (VQA) is a task to answer clinical questions, given a radiographic image, which is a challenging problem that requires a model to integrate both vision and language information.

Contrastive Learning Image-text matching +6