In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical labels, our architecture handles both continuous and discrete scales. Given pairwise comparisons of images, our model, called RankCGAN, performs two tasks: it learns to rank images using a subjective measure; and it learns a generative model that can be controlled by that measure. RankCGAN associates each subjective measure of interest to a distinct dimension of some latent space. We perform experiments on UT-Zap50K, PubFig and OSR datasets and demonstrate that the model is expressive and diverse enough to conduct two-attribute exploration and image editing.
@article{arxiv.1804.04082,
title = {Ranking CGANs: Subjective Control over Semantic Image Attributes},
author = {Yassir Saquil and Kwang In Kim and Peter Hall},
journal= {arXiv preprint arXiv:1804.04082},
year = {2018}
}