HIGHLIGHTS
- who: Stanislav Shimovolos et al. from the Moscow Institute of Physics and Technology, Moscow, Russia have published the paper: Adaptation to CT Reconstruction Kernels by Enforcing Cross-Domain Feature Maps Consistency, in the Journal: (JOURNAL)
- what: The authors show a decrease in the COVID-19 segmentation quality of the model trained on the smooth and tested on the sharp reconstruction kernels. The authors compare several domain adaptation approaches to tackle the problem such as task-specific augmentation and unsupervised adversarial learning. The authors propose the unsupervised adaptation method called F-Consistency that outperforms the previous . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.