On data augmentation for segmenting hyperspectral images

Jakub Nalepa; Michal Myller; Michal Kawulok; Bogdan Smolka

doi:10.1117/12.2519517

14 May 2019 On data augmentation for segmenting hyperspectral images

Jakub Nalepa, Michal Myller, Michal Kawulok, Bogdan Smolka

Proceedings Volume 10996, Real-Time Image Processing and Deep Learning 2019; 1099609 (2019) https://doi.org/10.1117/12.2519517
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Data augmentation is a popular technique which helps improve generalization capabilities of deep neural net- works, and can be perceived as implicit regularization. It is widely adopted in scenarios where acquiring high- quality training data is time-consuming and costly, with hyperspectral satellite imaging (HSI) being a real-life example. In this paper, we investigate data augmentation policies (exploiting various techniques, including generative adversarial networks applied to elaborate artificial HSI data) which help improve the generalization of deep neural networks (and other supervised learners) by increasing the representativeness of training sets. Our experimental study performed over HSI benchmarks showed that hyperspectral data augmentation boosts the classification accuracy of the models without sacrificing their real-time inference speed.

Conference Presentation

Citation Download Citation

Jakub Nalepa, Michal Myller, Michal Kawulok, and Bogdan Smolka "On data augmentation for segmenting hyperspectral images", Proc. SPIE 10996, Real-Time Image Processing and Deep Learning 2019, 1099609 (14 May 2019); https://doi.org/10.1117/12.2519517

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