CytoGAN: Generative Modeling of Cell Images
Peter Goldsborough, Nick Pawlowski, Juan Carlos Caicedo, Shantanu Singh, Anne Elizabeth Carpenter
Adversarially learned features group fluorescence images of chemically treated human cells better than autoencoder features, though classical computer vision and transfer learning still do better.
bioRxiv · Dec 2, 2017 · PreprintBioinformatics