Task-oriented synthetic-to-real image translation for data-efficient learning

Edgar A. Bernal; Rohan Sharma; Shanmukha Yenneti; Ian Mackey; Javier Malave; Derek J. Walvoord; Bernard Brower

doi:10.1117/12.3013814

7 June 2024 Task-oriented synthetic-to-real image translation for data-efficient learning

Edgar A. Bernal, Rohan Sharma, Shanmukha Yenneti, Ian Mackey, Javier Malave, Derek J. Walvoord, Bernard Brower

Proceedings Volume 13035, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II; 130350U (2024) https://doi.org/10.1117/12.3013814
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

Training state-of-the-art image classifiers and object detectors remains an extremely data-intensive process to this day. This is because inherently data-hungry, deep supervised networks are the traditional framework of choice. The significant data needs in turn impose strict requirements on the data acquisition, curation, and labelling stages that typically precede the learning process. This poses a particularly significant challenge for military and defense applications where the availability of high-quality labeled data is often limited. What is needed are methods that can effectively learn from sparse amounts of labeled, real-world data. In this paper, we propose a novel framework that incorporates a synthetic data generator into a supervised learning pipeline in order to enable end-to-end co-optimization of the discriminability and realism of the synthetic data, as well as the performance of the supervised engine. We demonstrate, via extensive empirical validation on image classification and object detection tasks, that the proposed framework is capable of learning from a small fraction of the real-world data required to train traditional, standalone supervised engines, while matching or even outperforming its off-the-shelf counterparts.

Conference Presentation

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

Citation Download Citation

Edgar A. Bernal, Rohan Sharma, Shanmukha Yenneti, Ian Mackey, Javier Malave, Derek J. Walvoord, and Bernard Brower "Task-oriented synthetic-to-real image translation for data-efficient learning", Proc. SPIE 13035, Synthetic Data for Artificial Intelligence and Machine Learning: Tools, Techniques, and Applications II, 130350U (7 June 2024); https://doi.org/10.1117/12.3013814

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