Continual domain adaptation under data constraints

Andreas Savakis

doi:10.1117/12.3025298

10 June 2024 Continual domain adaptation under data constraints

Andreas Savakis

Proceedings Volume 13036, Big Data VI: Learning, Analytics, and Applications; 1303602 (2024) https://doi.org/10.1117/12.3025298
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

The adaptation of deep network models to new environments, with significantly different distributions compared to the training data, has both theoretical interest and practical implications. Domain Adaptation (DA) aims to overcome the dataset bias problem by closing the gap in classification performance between the source domain used for training and the target domain where testing takes place. In this talk, we present a new framework for Continual Domain Adaptation, where the target domain samples are acquired in small batches over time and adaptation takes place continually in changing environments. Our Continual Domain Adaptation approach utilizes concepts from both DA and continual learning and demonstrate state-of-the-art results on various datasets under challenging conditions.

Conference Presentation

Citation Download Citation

Andreas Savakis "Continual domain adaptation under data constraints", Proc. SPIE 13036, Big Data VI: Learning, Analytics, and Applications, 1303602 (10 June 2024); https://doi.org/10.1117/12.3025298

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