An adaptive asymmetric loss function for positive unlabeled learning

Kristen Jaskie; Nolan Vaughn; Vivek Narayanaswamy; Sahba Zaare; Joseph Marvin; Andreas Spanias

doi:10.1117/12.2675650

13 June 2023 An adaptive asymmetric loss function for positive unlabeled learning

Kristen Jaskie, Nolan Vaughn, Vivek Narayanaswamy, Sahba Zaare, Joseph Marvin, Andreas Spanias

Proceedings Volume 12521, Automatic Target Recognition XXXIII; 125210U (2023) https://doi.org/10.1117/12.2675650
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

We introduce a new and efficient solution to the Positive and Unlabeled (PU) problem which is tailored specifically for a deep learning framework. We demonstrate the merit of this method using image classification. When only positive and unlabeled images are available for training, our custom loss function, paired with a simple linear transform of the output, results in an inductive classifier where no estimate of the class prior is required. This algorithm, known as the aaPU (Adaptive Asymmetric Positive Unlabeled) algorithm, provides near supervised classification accuracy with very low levels of labeled data on several image benchmark sets. aaPU demonstrates significant performance improvements over current state-of-the-art positive unlabeled learning algorithms.

Conference Presentation

Citation Download Citation

Kristen Jaskie, Nolan Vaughn, Vivek Narayanaswamy, Sahba Zaare, Joseph Marvin, and Andreas Spanias "An adaptive asymmetric loss function for positive unlabeled learning", Proc. SPIE 12521, Automatic Target Recognition XXXIII, 125210U (13 June 2023); https://doi.org/10.1117/12.2675650

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