Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning

arXiv:2402.15237v1 Announce Type: cross
Abstract: Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models. Since cross-modality medical data exhibit significant intra and inter-domain shifts and most are unlabelled, UDA is more important while challenging in medical image analysis. This paper proposes a simple yet potent contrastive learning framework for UDA to narrow the inter-domain gap between labelled source and unlabelled target distribution. Our method is validated on cerebral …

abstract arxiv brain cs.cv cs.lg data distribution domain domain adaptation image medical medical data predictive predictive models segmentation through type unsupervised