Extending deep learning to new classes without retraining

Jeffrey Schulz; Charlie Veal; Andrew Buck; Derek Anderson; James Keller; Mihail Popescu; Grant Scott; Dominic K. C. Ho; Timothy Wilkin

doi:10.1117/12.2558134

24 April 2020 Extending deep learning to new classes without retraining

Jeffrey Schulz, Charlie Veal, Andrew Buck, Derek Anderson, James Keller, Mihail Popescu, Grant Scott, Dominic K. C. Ho, Timothy Wilkin

Author Affiliations +

Proceedings Volume 11418, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXV; 1141803 (2020) https://doi.org/10.1117/12.2558134
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

The focus of this article is extending classifiers from N classes to N+1 classes without retraining for tasks like explosive hazard detection (EHD) and automatic target recognition (ATR). In recent years, deep learning has become state-of-the-art across domains. However, algorithms like convolutional neural networks (CNNs) suffer from the assumption of a closed-world model. That is, once a model is learned, a new class cannot usually be added without changes in the architecture and retraining. Herein, we put forth a way to extend a number of deep learning algorithms while keeping their features in a locked state; i.e., features are not retrained for the new N+1 class. Different feature transformations, metrics, and classifiers are explored to assess the degree to which a new sample belongs to one of the N classes and a decision rule is used for classification. Whereas this extends a deep learner, it does not tell us if a network with locked features has the potential to be extended. Therefore, we put forth a new method based on visually assessing cluster tendency to assess the degree to which a deep learner can be extended (or not). Lastly, while we are primarily focused on tasks like aerial EHD and ATR, experiments herein are for benchmark community data sets for sake of reproducible research.

Conference Presentation

Citation Download Citation

Jeffrey Schulz, Charlie Veal, Andrew Buck, Derek Anderson, James Keller, Mihail Popescu, Grant Scott, Dominic K. C. Ho, and Timothy Wilkin "Extending deep learning to new classes without retraining", Proc. SPIE 11418, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXV, 1141803 (24 April 2020); https://doi.org/10.1117/12.2558134

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