Swin transformer for hyperspectral rare sub-pixel target detection

Ludovic Girard; Vincent Roy; Thierry Eude; Philippe Giguère

doi:10.1117/12.2617779

31 May 2022 Swin transformer for hyperspectral rare sub-pixel target detection

Ludovic Girard, Vincent Roy, Thierry Eude, Philippe Giguère

Author Affiliations +

Proceedings Volume 12094, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXVIII; 120940Q (2022) https://doi.org/10.1117/12.2617779
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Transformers are becoming the state-of-the-art in multiple Computer vision (CV) and Natural language processing (NLP) tasks. As for hyperspectral target detection, a Transformer architecture named SpectralFormer2 has been developed and demonstrated improved performance over the previously state-of-the-art Convolutional neural network (CNN) architecture on widely studied classification tasks. The SpectralFormer was adapted from a CV architecture, the Vision Transformer (ViT). Concurrently, still in CV, a hierarchical and multi-scale version of the ViT, named Shifted windows (Swin) Transformer, is gaining momentum and is already the stateof-the-art on multiple tasks. In this paper, we adapt the Swin Transformer for hyperspectral classification and rare sub-pixel target detection. We apply this new architecture to commonly studied classification benchmarks public datasets such as Pavia University and Centre datasets, and to a new, large-scale airborne sub-pixel target detection dataset we developed. This new dataset is composed of over 100 M pixels taken over three collect days at three locations thousands of kilometers apart and in different climates. The proposed model reaches competitive performance on all of those tasks while reducing memory usage by 63 %.

Conference Presentation

Citation Download Citation

Ludovic Girard, Vincent Roy, Thierry Eude, and Philippe Giguère "Swin transformer for hyperspectral rare sub-pixel target detection", Proc. SPIE 12094, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imaging XXVIII, 120940Q (31 May 2022); https://doi.org/10.1117/12.2617779

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