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

With the current ubiquity of deep learning methods to solve computer visionand remote sensing specific tasks, the need for labelled data is growingconstantly. However, in many cases, the annotation process can be long andtedious depending on the expertise needed to perform reliable annotations. Inorder to alleviate this need for annotations, several self-supervised methodshave recently been proposed in the literature. The core principle behind thesemethods is to learn an image encoder using solely unlabelled data samples. Inearth observation, there are opportunities to exploit domain-specific remotesensing image data in order to improve these methods. Specifically, byleveraging the geographical position associated with each image, it is possibleto cross reference a location captured from multiple sensors, leading tomultiple views of the same locations. In this paper, we briefly review the coreprinciples behind so-called joint-embeddings methods and investigate the usageof multiple remote sensing modalities in self-supervised pre-training. Weevaluate the final performance of the resulting encoders on the task of methanesource classification.

Joint multi-modal Self-Supervised pre-training in Remote Sensing: Application to Methane Source Classification