1 code implementation • 12 Sep 2023 • Snigdha Sen, Saurabh Singh, Hayley Pye, Caroline M. Moore, Hayley Whitaker, Shonit Punwani, David Atkinson, Eleftheria Panagiotaki, Paddy J. Slator
Results: In simulations, ssVERDICT outperforms the baseline methods (NLLS and supervised DL) in estimating all the parameters from the VERDICT prostate model in terms of Pearson's correlation coefficient, bias, and MSE.
1 code implementation • 15 Feb 2022 • Eleni Chiou, Eleftheria Panagiotaki, Iasonas Kokkinos
In this work we challenge the common approach of using a one-to-one mapping ('translation') between the source and target domains in unsupervised domain adaptation (UDA).
1 code implementation • ICLR 2022 • Chen Jin, Ryutaro Tanno, Thomy Mertzanidou, Eleftheria Panagiotaki, Daniel C. Alexander
Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget.
no code implementations • 19 Sep 2021 • Eleni Chiou, Francesco Giganti, Shonit Punwani, Iasonas Kokkinos, Eleftheria Panagiotaki
Firstly, we introduce a semantic cycle-consistency loss in the source domain to ensure that the translation preserves the semantics.
2 code implementations • 14 Oct 2020 • Eleni Chiou, Francesco Giganti, Shonit Punwani, Iasonas Kokkinos, Eleftheria Panagiotaki
Domain adaptation methods partially mitigate this problem by translating training data from a related source domain to a novel target domain, but typically assume that a one-to-one translation is possible.