Application specificity of data for pre-training in computer vision

Gabriel G. Peters; Scott D. Couwenhoven; Derek J. Walvoord; Carl Salvaggio

doi:10.1117/12.3013088

6 June 2024 Application specificity of data for pre-training in computer vision

Gabriel G. Peters, Scott D. Couwenhoven, Derek J. Walvoord, Carl Salvaggio

Proceedings Volume 13058, Disruptive Technologies in Information Sciences VIII; 1305803 (2024) https://doi.org/10.1117/12.3013088
Event: SPIE Defense + Commercial Sensing, 2024, National Harbor, Maryland, United States

Abstract

In an era of immense data generation, unlocking the full potential of Machine Learning (ML) hinges on overcoming the limitations posed by the scarcity of labeled data. In Computer Vision (CV) research, algorithm design must consider this shift and focus instead on the abundance of unlabeled imagery. In recent years, there has been a notable trend within the community toward Self-Supervised Learning (SSL) methods that can leverage this untapped data pool. ML practice promotes self-supervised pre-training for generalized feature extraction on a diverse unlabeled dataset followed by supervised transfer learning on a smaller set of labeled, application-specific images. This shift in learning methods elicits conversation about the importance of pre-training data composition for optimizing downstream performance. We evaluate models with varying measures of similarity between pre-training and transfer learning data compositions. Our findings indicate that front-end embeddings sufficiently generalize learned image features independent of data composition, leaving transfer learning to inject the majority of application-specific understanding into the model. Composition may be irrelevant in self-supervised pre-training, suggesting target data is a primary driver of application specificity. Thus, pre-training deep learning models with application-specific data, which is often difficult to acquire, is not necessary for reaching competitive downstream performance. The capability to pre-train on more accessible datasets invites more flexibility in practical deep learning.

Conference Presentation

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

Citation Download Citation

Gabriel G. Peters, Scott D. Couwenhoven, Derek J. Walvoord, and Carl Salvaggio "Application specificity of data for pre-training in computer vision", Proc. SPIE 13058, Disruptive Technologies in Information Sciences VIII, 1305803 (6 June 2024); https://doi.org/10.1117/12.3013088

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