Source-Free Unsupervised Domain Adaptation with Norm and Shape Constraints for Medical Image Segmentation
Unsupervised domain adaptation (UDA) is one of the key technologies to solve a problem where it is hard to obtain ground truth labels needed for supervised learning. In general, UDA assumes that all samples from source and target domains are available during the training process. However, this is not a realistic assumption under applications where data privacy issues are concerned. To overcome this limitation, UDA without source data, referred to source-free unsupervised domain adaptation (SFUDA) has been recently proposed. Here, we propose a SFUDA method for medical image segmentation. In addition to the entropy minimization method, which is commonly used in UDA, we introduce a loss function for avoiding feature norms in the target domain small and a prior to preserve shape constraints of the target organ. We conduct experiments using datasets including multiple types of source-target domain combinations in order to show the versatility and robustness of our method. We confirm that our method outperforms the state-of-the-art in all datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationImage SegmentationMedical Image SegmentationSemantic SegmentationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation
Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usual…
Autonomous DrivingDomain AdaptationSemantic SegmentationUnsupervised Domain AdaptationJacobian Norm for Unsupervised Source-Free Domain Adaptation
Unsupervised Source (data) Free domain adaptation (USFDA) aims to transfer knowledge from a well-trained source model to a related but unlabeled target domain. In such a scenario, all conventional adaptation methods that…
Domain AdaptationSource-Free Domain AdaptationSource-Free Domain Adaptation for Real-world Image Dehazing
Deep learning-based source dehazing methods trained on synthetic datasets have achieved remarkable performance but suffer from dramatic performance degradation on real hazy images due to domain shift. Although certain Do…
Domain AdaptationImage DehazingSource-Free Domain AdaptationUnsupervised Domain AdaptationKey Design Choices for Double-Transfer in Source-Free Unsupervised Domain Adaptation
Fine-tuning and Domain Adaptation emerged as effective strategies for efficiently transferring deep learning models to new target tasks. However, target domain labels are not accessible in many real-world scenarios. This…
Domain AdaptationUnsupervised Domain AdaptationFVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model usi…
Domain AdaptationImage SegmentationMedical Image SegmentationSegmentation+3