English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large, self-supervised vision models have led to substantial advancements forautomatically interpreting natural images. Recent works have begun tailoringthese methods to remote sensing data which has rich structure withmulti-sensor, multi-spectral, and temporal information providing massiveamounts of self-labeled data that can be used for self-supervised pre-training.In this work, we develop a new encoder architecture called USat that can inputmulti-spectral data from multiple sensors for self-supervised pre-training.USat is a vision transformer with modified patch projection layers andpositional encodings to model spectral bands with varying spatial scales frommultiple sensors. We integrate USat into a Masked Autoencoder (MAE)self-supervised pre-training procedure and find that a pre-trained USatoutperforms state-of-the-art self-supervised MAE models trained on remotesensing data on multiple remote sensing benchmark datasets (up to 8%) and leadsto improvements in low data regimes (up to 7%). Code and pre-trained weightsare available at https://github.com/stanfordmlgroup/USat .

USat: A Unified Self-Supervised Encoder for Multi-Sensor Satellite Imagery