Sökning: onr:"swepub:oai:DiVA.org:kth-322794" >
What Makes Transfer...
What Makes Transfer Learning Work for Medical Images : Feature Reuse & Other Factors
-
- Matsoukas, Christos (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Stockholm, Sweden.;Sci Life Lab, Stockholm, Sweden.;AstraZeneca, Gothenburg, Sweden.
-
- Fredin Haslum, Johan (författare)
- KTH,Beräkningsvetenskap och beräkningsteknik (CST),Science for Life Laboratory, SciLifeLab,AstraZeneca, Gothenburg, Sweden.
-
- Sorkhei, Moein (författare)
- KTH,Intelligenta system,Science for Life Laboratory, SciLifeLab
-
visa fler...
-
- Soderberg, Magnus (författare)
- AstraZeneca, Gothenburg, Sweden.
-
- Smith, Kevin, 1975- (författare)
- KTH,Science for Life Laboratory, SciLifeLab,Beräkningsvetenskap och beräkningsteknik (CST)
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2022
- 2022
- Engelska.
-
Ingår i: 2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR). - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 9215-9224
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Matematik -- Beräkningsmatematik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Computational Mathematics (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)