@inproceedings{pmlr-v70-odena17a,
address = {International Convention Centre, Sydney, Australia},
author = {Odena, Augustus and Olah, Christopher and Shlens, Jonathon},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
editor = {Precup, Doina and Teh, Yee Whye},
pages = {2642--2651},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
title = {{Conditional Image Synthesis with Auxiliary Classifier {\{}GAN{\}}s}},
url = {http://proceedings.mlr.press/v70/odena17a.html},
volume = {70},
year = {2017}
}
This paper leveraged some techniques to improved GAN variant called AC-GAN. In addition, they also proposed methods for measuring the extent to which a model makes use of its given output resolution, methods for measuring perceptual variability of samples from the model.
The code is here