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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Self-supervision based deep learning classification approaches have receivedconsiderable attention in academic literature. However, the performance of suchmethods on remote sensing imagery domains remains under-explored. In this work,we explore contrastive representation learning methods on the task ofimagery-based city classification, an important problem in urban computing. Weuse satellite and map imagery across 2 domains, 3 million locations and morethan 1500 cities. We show that self-supervised methods can build ageneralizable representation from as few as 200 cities, with representationsachieving over 95\% accuracy in unseen cities with minimal additional training.We also find that the performance discrepancy of such methods, when compared tosupervised methods, induced by the domain discrepancy between natural imageryand abstract imagery is significant for remote sensing imagery. We compare allanalysis against existing supervised models from academic literature andopen-source our models for broader usage and further criticism.

Self-Supervision. Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations