Into the wild: a study in rendered synthetic data and domain adaptation methods

Marissa Dotter; Chelsea Mediavilla; Jonathan Sato; Chris M. Ward; Shibin Parameswaran; Josh Harguess

doi:10.1117/12.2518774

4 June 2019 Into the wild: a study in rendered synthetic data and domain adaptation methods

Marissa Dotter, Chelsea Mediavilla, Jonathan Sato, Chris M. Ward, Shibin Parameswaran, Josh Harguess

Proceedings Volume 10992, Geospatial Informatics IX; 109920D (2019) https://doi.org/10.1117/12.2518774
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Rendering synthetic imagery from gaming engine environments allows us to create data featuring any number of object orientations, conditions, and lighting variations. This capability is particularly useful in classification tasks, where there is an overwhelming lack of labeled data needed to train state-of-the-art machine learning algorithms. However, the use of synthetic data is not without limit: in the case of imagery, training a deep learning model on purely synthetic data typically yields poor results when applied to real world imagery. Previous work shows that "domain adaptation," mixing real-world and synthetic data, improves performance on a target dataset. In this paper, we train a deep neural network with synthetic imagery, including ordnance and overhead ship imagery and investigate a variety of methods to adapt our model to a dataset of real images.

Conference Presentation

Citation Download Citation

Marissa Dotter, Chelsea Mediavilla, Jonathan Sato, Chris M. Ward, Shibin Parameswaran, and Josh Harguess "Into the wild: a study in rendered synthetic data and domain adaptation methods", Proc. SPIE 10992, Geospatial Informatics IX, 109920D (4 June 2019); https://doi.org/10.1117/12.2518774

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