Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes
Abstract
Recent advances in Deep Learning and probabilistic modeling have let to strong improvements in generative models for images. On the one hand, GANs have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, CVAE models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective enforces coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity.
Cite
Text
He et al. "Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01270-0_25Markdown
[He et al. "Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/he2018eccv-diverse/) doi:10.1007/978-3-030-01270-0_25BibTeX
@inproceedings{he2018eccv-diverse,
title = {{Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes}},
author = {He, Yang and Schiele, Bernt and Fritz, Mario},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01270-0_25},
url = {https://mlanthology.org/eccv/2018/he2018eccv-diverse/}
}