InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models
InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models
复制标题
DOI：
10.1609/aaai.v34i04.5863
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Ameya Joshi;Minsu Cho;Viraj Shah;B. Pokuri;S. Sarkar;B. Ganapathysubramanian;C. Hegde
中科院分区：
文献类型：
--
作者：
Ameya Joshi;Minsu Cho;Viraj Shah;B. Pokuri;S. Sarkar;B. Ganapathysubramanian;C. Hegde
生成性对抗网络(GANS)虽然在模拟复杂数据分布方面取得了广泛的成功，但在科学计算和设计中还没有得到充分的利用。出现这种情况的原因包括GAN表示离散值图像数据缺乏灵活性，以及对生成样本的物理属性缺乏控制。我们提出了一种新的条件产生式建模方法(InvNet)，该方法能够有效地对离散值图像进行建模，同时允许控制其参数化的几何和统计属性。我们在几个合成和现实世界的问题上评估了我们的方法：导航具有所需尺寸的几何形状的流形；二元两相材料的生成；以及生成多取向多晶微结构的(具有挑战性的)问题。
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.