Toward quantifying the real-versus-synthetic imagery training data reality gap: analysis and practical applications

Colin N. Reinhardt; Sarah Brockman; Rusty Blue; Brian Clipp; Anthony Hoogs

doi:10.1117/12.3026764

7 June 2024 Toward quantifying the real-versus-synthetic imagery training data reality gap: analysis and practical applications

Colin N. Reinhardt, Sarah Brockman, Rusty Blue, Brian Clipp, Anthony Hoogs

Author Affiliations +

Proceedings Volume 13035, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II; 130350W (2024) https://doi.org/10.1117/12.3026764
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

Synthetically-generated imagery holds the promise of being a panacea for the challenges of real world datasets. Yet it continues to be frequently observed that deep learning model performance is not as good when trained with synthetic data versus real measured imagery. In this study we present analyses and illustration of the use of several statistical metrics, measures, and visualization tools based on the distance and similarity between real and synthetic data empirical distributions in the latent feature embedding space, which provide a quantitative understanding of the relevant image-domain distribution discrepancy issues hampering the generation of performant simulated datasets. We also demonstrate the practical applications of these tools and techniques in a novel study comparing latent space embedding vector distributions of real, pristine synthetic, and synthetic modified by physics-based degradation models. The results may assist deep learning practitioners and synthetic imagery modelers with evaluating latent space embedding distributional dissimilarity and improving model performance when using simulation tools to generate synthetic imagery training data.

Conference Presentation

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Colin N. Reinhardt, Sarah Brockman, Rusty Blue, Brian Clipp, and Anthony Hoogs "Toward quantifying the real-versus-synthetic imagery training data reality gap: analysis and practical applications", Proc. SPIE 13035, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II, 130350W (7 June 2024); https://doi.org/10.1117/12.3026764

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