Evaluating the label efficiency of contrastive self-supervised learning for multi-resolution satellite imagery

Jules Bourcier; Gohar Dashyan; Jocelyn Chanussot; Karteek Alahari

doi:10.1117/12.2636350

26 October 2022 Evaluating the label efficiency of contrastive self-supervised learning for multi-resolution satellite imagery

Jules Bourcier, Gohar Dashyan, Jocelyn Chanussot, Karteek Alahari

Author Affiliations +

Proceedings Volume 12267, Image and Signal Processing for Remote Sensing XXVIII; 122670K (2022) https://doi.org/10.1117/12.2636350
Event: SPIE Remote Sensing, 2022, Berlin, Germany

Abstract

The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize efficiently from limited amounts of labeled data, allowing us to tackle a wider range of Earth observation tasks. Another challenge in this domain is developing algorithms that operate at variable spatial resolutions, e.g., for the problem of classifying land use at different scales. Recently, self-supervised learning has been applied in the remote sensing domain to exploit readily-available unlabeled data, and was shown to reduce or even close the gap with supervised learning. In this paper, we study self-supervised visual representation learning through the lens of label efficiency, for the task of land use classification on multi-resolution/multi-scale satellite images. We benchmark two contrastive self-supervised methods adapted from Momentum Contrast (MoCo) and provide evidence that these methods can be perform effectively given little downstream supervision, where randomly initialized networks fail to generalize. Moreover, they outperform out-of-domain pretraining alternatives. We use the large-scale fMoW dataset to pretrain and evaluate the networks, and validate our observations with transfer to the RESISC45 dataset.

Conference Presentation

Citation Download Citation

Jules Bourcier, Gohar Dashyan, Jocelyn Chanussot, and Karteek Alahari "Evaluating the label efficiency of contrastive self-supervised learning for multi-resolution satellite imagery", Proc. SPIE 12267, Image and Signal Processing for Remote Sensing XXVIII, 122670K (26 October 2022); https://doi.org/10.1117/12.2636350

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