InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models
Abstract
Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.
Cite
Text
Joshi et al. "InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I04.5863Markdown
[Joshi et al. "InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/joshi2020aaai-invnet/) doi:10.1609/AAAI.V34I04.5863BibTeX
@inproceedings{joshi2020aaai-invnet,
title = {{InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models}},
author = {Joshi, Ameya and Cho, Minsu and Shah, Viraj and Pokuri, Balaji Sesha Sarath and Sarkar, Soumik and Ganapathysubramanian, Baskar and Hegde, Chinmay},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2020},
pages = {4377-4384},
doi = {10.1609/AAAI.V34I04.5863},
url = {https://mlanthology.org/aaai/2020/joshi2020aaai-invnet/}
}