Source-free domain adaptive segmentation with class-balanced complementary self-training-Reference-Cited by-同舟云学术

Source-free domain adaptive segmentation with class-balanced complementary self-training

Published:2023-12 Issue: Volume:146 Page:102694
ISSN:0933-3657
Container-title:Artificial Intelligence in Medicine
language:en
Short-container-title:Artificial Intelligence in Medicine

Author:

Huang Yongsong^ORCID,Xie Wanqing,Li Mingzhen,Xiao Ethan,You Jane,Liu Xiaofeng^ORCID

Funder

Japan Society for the Promotion of Science

National Key Research and Development Program of China

Publisher

Elsevier BV

Subject

Artificial Intelligence,Medicine (miscellaneous)

Reference43 articles.

1. Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation;Tajbakhsh;Med Image Anal,2020

2. Vicinal feature statistics augmentation for federated 3D medical volume segmentation;Huang,2023

3. Memory consistent unsupervised off-the-shelf model adaptation for source-relaxed medical image segmentation;Liu;Med Image Anal,2023

4. Xie W, Li M, Wu J, Huang Y, Bu Y, University&HMS S, You J, PolyU H, Liu X. Learn Complementary Pseudo-label for Source-free Domain Adaptive Medical Segmentation. In: Proc. NeurIPS workshops. 2022.

5. Deep unsupervised domain adaptation: A review of recent advances and perspectives;Liu;APSIPA Trans Signal Inf Process,2022

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. CoST-UNet: Convolution and swin transformer based deep learning architecture for cardiac segmentation;Biomedical Signal Processing and Control;2024-10

2. Learn from orientation prior for radiograph super-resolution: Orientation operator transformer;Computer Methods and Programs in Biomedicine;2024-03