UDCT: Unsupervised data to content transformation with histogram-matching cycle-consistent generative adversarial networks
S. J. Ihle, A. M. Reichmuth, S. Girardin, H. Han, F. Stauffer, A. Bonnin, M. F. M. Stampanoni, J. Voros, C. Forro
This paper introduces an unsupervised image segmentation method using cycleGAN-inspired techniques and benchmarks it against a supervised network on cell-counting tasks.
bioRxiv · Mar 1, 2019Bioengineering