One of the biggest challenges in the research of generative adversarial networks (GANs) is assessing the quality of generated samples and detecting various levels of mode collapse. In this work, we construct a novel measure of performance of a GAN by comparing geometrical properties of the underlying data manifold and the generated one, which provides both qualitative and quantitative means for evaluation. Our algorithm can be applied to datasets of an arbitrary nature and is not limited to visual data. We test the obtained metric on various real-life models and datasets and demonstrate that our method provides new insights into properties of GANs.
Valentin Khrulkov (Skolkovo Institute Of Science And Technology)
Ivan Oseledets (Skoltech)
Related Events (a corresponding poster, oral, or spotlight)
2018 Oral: Geometry Score: A Method For Comparing Generative Adversarial Networks »
Thu Jul 12th 09:00 -- 09:20 AM Room A7