Augmenting saliency maps with uncertainty

Supriyo Chakraborty; Prudhvi Gurram; Franck Le; Lance Kaplan; Richard Tomsett

doi:10.1117/12.2588026

12 April 2021 Augmenting saliency maps with uncertainty

Supriyo Chakraborty, Prudhvi Gurram, Franck Le, Lance Kaplan, Richard Tomsett

Proceedings Volume 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III; 117461M (2021) https://doi.org/10.1117/12.2588026
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Explanations are generated to accompany a model decision indicating features of the input data that were the most relevant towards the model decision. Explanations are important not only for understanding the decisions of deep neural network, which in spite of their their huge success in multiple domains operate largely as abstract black boxes, but also for other model classes such as gradient boosted decision trees. In this work, we propose methods, using both Bayesian and Non-Bayesian approaches to augment explanations with uncertainty scores. We believe that uncertainty augmented saliency maps can help in better calibration of the trust between human analyst and the machine learning models.

Conference Presentation

Citation Download Citation

Supriyo Chakraborty, Prudhvi Gurram, Franck Le, Lance Kaplan, and Richard Tomsett "Augmenting saliency maps with uncertainty", Proc. SPIE 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, 117461M (12 April 2021); https://doi.org/10.1117/12.2588026

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