Open this publication in new window or tab >>Show others...
2022 (English)In: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR), Institute of Electrical and Electronics Engineers (IEEE) , 2022, p. 9215-9224Conference paper, Published paper (Refereed)
Abstract [en]
Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has become the de-facto approach, despite differences in the tasks and image characteristics between the domains. However, it is unclear what factors determine whether - and to what extent transfer learning to the medical domain is useful. The longstanding assumption that features from the source domain get reused has recently been called into question. Through a series of experiments on several medical image benchmark datasets, we explore the relationship between transfer learning, data size, the capacity and inductive bias of the model, as well as the distance between the source and target domain. Our findings suggest that transfer learning is beneficial in most cases, and we characterize the important role feature reuse plays in its success.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022
Series
IEEE Conference on Computer Vision and Pattern Recognition, ISSN 1063-6919
National Category
Computational Mathematics
Identifiers
urn:nbn:se:kth:diva-322794 (URN)10.1109/CVPR52688.2022.00901 (DOI)000870759102028 ()2-s2.0-85137378486 (Scopus ID)
Conference
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), JUN 18-24, 2022, New Orleans, LA
Note
Part of proceedings ISBN 978-1-6654-6946-3
QC 20230131
2023-01-312023-01-312024-05-20Bibliographically approved