Impact of model architecture on robustness and interpretability of multispectral deep learning models

Charles Godfrey; Elise Bishoff; Myles McKay; Eleanor Byler

doi:10.1117/12.2662998

13 June 2023 Impact of model architecture on robustness and interpretability of multispectral deep learning models

Charles Godfrey, Elise Bishoff, Myles McKay, Eleanor Byler

Proceedings Volume 12519, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX ; 125190L (2023) https://doi.org/10.1117/12.2662998
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Including information from additional spectral bands (e.g., near-infrared) can improve deep learning model performance for many vision-oriented tasks. There are many possible ways to incorporate this additional information into a deep learning model, but the optimal fusion strategy has not yet been determined and can vary between applications. At one extreme, known as “early fusion,” additional bands are stacked as extra channels to obtain an input image with more than three channels. At the other extreme, known as “late fusion,” RGB and non-RGB bands are passed through separate branches of a deep learning model and merged immediately before a final classification or segmentation layer. In this work, we characterize the performance of a suite of multispectral deep learning models with different fusion approaches, quantify their relative reliance on different input bands and evaluate their robustness to naturalistic image corruptions affecting one or more input channels.

Conference Presentation

Citation Download Citation

Charles Godfrey, Elise Bishoff, Myles McKay, and Eleanor Byler "Impact of model architecture on robustness and interpretability of multispectral deep learning models", Proc. SPIE 12519, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXIX , 125190L (13 June 2023); https://doi.org/10.1117/12.2662998

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