. Author manuscript; available in PMC: 2021 Oct 20.

Published in final edited form as: IEEE Int Conf Comput Vis Workshops. 2020 Mar 5;2019:10.1109/iccvw.2019.00043. doi: 10.1109/iccvw.2019.00043

Table 2.

DAL results. Estimated lowerbound and upperbound for cross-modality liver segmentation with DAL. Comparison of segmentation results for domain adaptation with different models. Our DALACE generalizes well to the DAL task compared to other methods.

DAL task	DSC (std)
lowerbound	0.228 (0.130)
upperbound	0.823 (0.057)
Method	DSC (std)

CycleGAN [26]	0.522 (0.064)
TD-GAN [25]	0.719 (0.089)
DADR [24]	0.742 (0.045)
DALACE	0.794 (0.044)