InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models


  • Ameya Joshi Iowa State University
  • Minsu Cho Iowa State University
  • Viraj Shah Iowa State University
  • Balaji Pokuri Iowa State University
  • Soumik Sarkar Iowa State University
  • Baskar Ganapathysubramanian Iowa State University
  • Chinmay Hegde Iowa State University



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.




How to Cite

Joshi, A., Cho, M., Shah, V., Pokuri, B., Sarkar, S., Ganapathysubramanian, B., & Hegde, C. (2020). InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 4377-4384.



AAAI Technical Track: Machine Learning