In addition, we propose training a semantic segmentation network along with the translation task, and to leverage this output as a loss term that improves robustness.
State-of-the-art image-to-image translation methods tend to struggle in an imbalanced domain setting, where one image domain lacks richness and diversity.
The network is trained on the two input images only, learns their internal statistics and correlations, and applies them to up-sample the target modality.
In this work, we bypass the difficulties of developing cross-modality similarity measures, by training an image-to-image translation network on the two input modalities.
In this paper we perform image resizing in feature space where the deep layers of a neural network contain rich important semantic information.
As a result, in recent years more attention has been given to techniques that learn the mapping from unpaired sets.