Using deep perceptual embeddings as a quality metric for synthetic imagery

William Luer; Josh Harguess

doi:10.1117/12.2587943

12 April 2021 Using deep perceptual embeddings as a quality metric for synthetic imagery

William Luer, Josh Harguess

Proceedings Volume 11733, Geospatial Informatics XI; 1173306 (2021) https://doi.org/10.1117/12.2587943
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

The potential of synthetic image generation in machine learning applications has a myriad of both benefits and drawbacks. Synthetic datasets are valuable when real datasets are costly to acquire or difficult to share. Although synthetic imagery has improved in quality over the years, automated evaluation of the synthetic data remains challenging. For example, the Fréchet inception distance does not always correlate with perceptual quality and the perceptual path length operates at the model level rather than the data level. In this work, we propose a new evaluation metric that both correlates with perceptual quality and operates at the data level so that it can function on datasets from any domain. We do this by mapping high dimensional images into a lower dimensional, perceptually disentangled embedding space and computing the distance between distributions of embeddings within this space. We utilize a convolutional autoencoder trained with a linear combination of pixelwise and perceptual losses to perform the mapping and use existing metrics to measure the distance between the distributions of embeddings. We demonstrate efficacy of this metric on the CIFAR-10 dataset.

Conference Presentation

Citation Download Citation

William Luer and Josh Harguess "Using deep perceptual embeddings as a quality metric for synthetic imagery", Proc. SPIE 11733, Geospatial Informatics XI, 1173306 (12 April 2021); https://doi.org/10.1117/12.2587943

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