Neural network classification of degraded imagery using soft labels: towards human-level performance with “accurate” likelihoods?

Jeffery R. Philson

doi:10.1117/12.2520072

14 May 2019 Neural network classification of degraded imagery using soft labels: towards human-level performance with “accurate” likelihoods?

Jeffery R. Philson

Author Affiliations +

Proceedings Volume 10988, Automatic Target Recognition XXIX; 109880P (2019) https://doi.org/10.1117/12.2520072
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

The vast majority of recent progress in deep learning for computer vision has been demonstrated on problems with low irreducible error rates. While it is natural to use hard “one-hot” encoded training labels for such problems, this may not be the case in applications with large irreducible error. This includes classification problems on severely degraded or classambiguous imagery. Furthermore, databases primarily consisting of degraded examples are difficult to diagnose in terms of assuring that non-causal statistical correlations across the training and test sets do not exist for certain classes. Expert image analysts however, are typically well-regularized and will not overfit to such correlations. In this work, soft labels are applied to a surrogate problem with large irreducible error, where the labels are generated by an ensemble of networks serving as a proxy for human expert labelers. Results of networks trained on these soft targets, versus their one-hot counterparts are compared. A concept for an “imagination mechanism” in neural networks training on soft labels is also introduced.

Conference Presentation

Citation Download Citation

Jeffery R. Philson "Neural network classification of degraded imagery using soft labels: towards human-level performance with “accurate” likelihoods?", Proc. SPIE 10988, Automatic Target Recognition XXIX, 109880P (14 May 2019); https://doi.org/10.1117/12.2520072

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