Increasing the Diversity of Deep Generative Models
Abstract
Generative models are used in a variety of applications that require diverse output. Yet, models are primarily optimised for sample fidelity and mode coverage. My work aims to increase the output diversity of generative models for multi-solution tasks. Previously, we analysed the use of generative models in artistic settings and how its objective diverges from distribution fitting. For specific use cases, we quantified the limitations of generative models. Future work will focus on adapting generative modelling for downstream tasks that require a diverse set of high-quality artefacts.
Cite
Text
Berns. "Increasing the Diversity of Deep Generative Models." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21572Markdown
[Berns. "Increasing the Diversity of Deep Generative Models." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/berns2022aaai-increasing/) doi:10.1609/AAAI.V36I11.21572BibTeX
@inproceedings{berns2022aaai-increasing,
title = {{Increasing the Diversity of Deep Generative Models}},
author = {Berns, Sebastian},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {12870-12871},
doi = {10.1609/AAAI.V36I11.21572},
url = {https://mlanthology.org/aaai/2022/berns2022aaai-increasing/}
}