Efficient ATR using contrastive learning

Attiano Purpura-Pontoniere; Abdullah-Al-Zubaer Imran; Tarun Bhattacharya

doi:10.1117/12.2616822

31 May 2022 Efficient ATR using contrastive learning

Attiano Purpura-Pontoniere, Abdullah-Al-Zubaer Imran, Tarun Bhattacharya

Proceedings Volume 12096, Automatic Target Recognition XXXII; 120960H (2022) https://doi.org/10.1117/12.2616822
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Automatic Target Recognition (ATR) is a valuable application of computer vision that traditionally requires copious and tedious labeling through supervised learning. This research explored if ATR can be performed on satellite imagery at a comparable accuracy to a fully supervised baseline model with a considerably smaller subset of data labelled, on the order of 10%, using a recently developed semi-supervised technique, contrastive learning. Supervised contrastive loss was explored and compared to traditional cross entropy loss. Supervised contrastive loss was found to perform significantly better with a subset of the data labelled on the XView dataset, a publicly available dataset of satellite imagery captured with .3 meter ground sampling. The caveats when nothing and everything is labelled were additionally explored.

Conference Presentation

Citation Download Citation

Attiano Purpura-Pontoniere, Abdullah-Al-Zubaer Imran, and Tarun Bhattacharya "Efficient ATR using contrastive learning", Proc. SPIE 12096, Automatic Target Recognition XXXII, 120960H (31 May 2022); https://doi.org/10.1117/12.2616822

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