A few shots at few shot learning

Donald Waagen; Don Hulsey; David Gray

doi:10.1117/12.2661719

13 June 2023 A few shots at few shot learning

Donald Waagen, Don Hulsey, David Gray

Proceedings Volume 12521, Automatic Target Recognition XXXIII; 125210H (2023) https://doi.org/10.1117/12.2661719
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Deep learning models are currently the models of choice for image classification tasks. But large scale models require large quantities of data. For many tasks, acquiring a sufficient quantity of training data is not feasible. Because of this, an active area of research in machine learning is the field of few sample learning or few shot learning (FSL), with architectures that attempt to build effective models for a low-sample regime. In this paper, we focus on the established few-shot learning algorithm developed by Snell et al.1 We propose an FSL model where the model is produced via traditional encoding with the backend output layer replaced with the prototypical clustering classifier of Snell et al.. We hypothesize that this algorithm’s encoding structure produced by this training may be equivalent to models produced by traditional cross-entropy deep learning optimization. We compare few shot classification performance on unseen classes between models trained using the FSL training paradigm and our hybrid models trained traditionally with softmax, but modified for FSL use. Our empirical results indicate that traditionally trained models can be effectively re-used for few sample classification.

Conference Presentation

Citation Download Citation

Donald Waagen, Don Hulsey, and David Gray "A few shots at few shot learning", Proc. SPIE 12521, Automatic Target Recognition XXXIII, 125210H (13 June 2023); https://doi.org/10.1117/12.2661719

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