1 code implementation • 31 Jul 2022 • Ivan Zakazov, Vladimir Shaposhnikov, Iaroslav Bespalov, Dmitry V. Dylov
Generalizability of deep learning models may be severely affected by the difference in the distributions of the train (source domain) and the test (target domain) sets, e. g., when the sets are produced by different hardware.
1 code implementation • 10 Jul 2021 • Ivan Zakazov, Boris Shirokikh, Alexey Chernyavskiy, Mikhail Belyaev
Domain Adaptation (DA) methods are widely used in medical image segmentation tasks to tackle the problem of differently distributed train (source) and test (target) data.
1 code implementation • 17 Aug 2020 • Boris Shirokikh, Ivan Zakazov, Alexey Chernyavskiy, Irina Fedulova, Mikhail Belyaev
Our results demonstrate that 1) domain-shift may deteriorate the quality even for a simple brain extraction segmentation task (surface Dice Score drops from 0. 85-0. 89 even to 0. 09); 2) fine-tuning of the first layers significantly outperforms fine-tuning of the last layers in almost all supervised domain adaptation setups.