Identifying the advantageous latent space dimensionality for StyleGANs used in industrial machine vision applications

Dominik Wolfschläger; Ruslan Yermakov; Benjamin Montavon; Benjamin Berkels; Robert H. Schmitt

doi:10.1117/12.2646326

15 March 2023 Identifying the advantageous latent space dimensionality for StyleGANs used in industrial machine vision applications

Dominik Wolfschläger, Ruslan Yermakov, Benjamin Montavon, Benjamin Berkels, Robert H. Schmitt

Author Affiliations +

Proceedings Volume 12438, AI and Optical Data Sciences IV; 124380R (2023) https://doi.org/10.1117/12.2646326
Event: SPIE OPTO, 2023, San Francisco, California, United States

Abstract

State-of-the-art style-based generative adversarial networks (StyleGANs) synthesize high-quality images by learning a mapping from a disentangled latent space onto the image manifold. Thereby, learned representations can be analyzed by interpreting the latent space and used subsequently to control the properties of the synthesized industrial machine vision data. StyleGANs in combination with an embedding into the latent space enable the assessment of the properties of embedded images by means of their latent space representations, however, a trade-off between the dimensionality of the StyleGAN’s latent space and the quality of generated images must be found. While a smaller latent space is easier to interpret, it might not capture all quality characteristics if lossless compression cannot be achieved. This work presents an evaluation scheme that uses statistical hypothesis testing to identify an advantageous dimensionality of the latent space for industrial machine vision applications. As quality measure of images synthesized by GANs, often the Fr´echet Inception distance (FID) based on features learned from the ImageNet dataset is used. However, the features of the underlying Inception network are opaque and might not be representative for application specific quality characteristics. Herein, synthetic data is evaluated instead by means of a Fr´echet distance based on selected and application specific features extracted from the used industrial machine vision dataset. With these application specific features, the image quality of multiple StyleGANs trained with different latent space dimensionalities is compared using statistical tests to select an advantageous latent space dimension.

Conference Presentation

Citation Download Citation

Dominik Wolfschläger, Ruslan Yermakov, Benjamin Montavon, Benjamin Berkels, and Robert H. Schmitt "Identifying the advantageous latent space dimensionality for StyleGANs used in industrial machine vision applications", Proc. SPIE 12438, AI and Optical Data Sciences IV, 124380R (15 March 2023); https://doi.org/10.1117/12.2646326

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available