Share Email Print

Proceedings Paper

Into the wild: a study in rendered synthetic data and domain adaptation methods
Author(s): Marissa Dotter; Chelsea Mediavilla; Jonathan Sato; Chris M. Ward; Shibin Parameswaran; Josh Harguess
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 4 June 2019
PDF: 11 pages
Proc. SPIE 10992, Geospatial Informatics IX, 109920D (4 June 2019); doi: 10.1117/12.2518774
Show Author Affiliations
Marissa Dotter, Naval Information Warfare Ctr. Pacific (United States)
Chelsea Mediavilla, Naval Information Warfare Ctr. Pacific (United States)
Jonathan Sato, Naval Information Warfare Ctr. Pacific (United States)
Chris M. Ward, Naval Information Warfare Ctr. Pacific (United States)
Shibin Parameswaran, Naval Information Warfare Ctr. Pacific (United States)
Josh Harguess, Naval Information Warfare Ctr. Pacific (United States)

Published in SPIE Proceedings Vol. 10992:
Geospatial Informatics IX
Kannappan Palaniappan; Peter J. Doucette; Gunasekaran Seetharaman, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?