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

The application of deep neural networks to remote sensing imagery is oftenconstrained by the lack of ground-truth annotations. Adressing this issuerequires models that generalize efficiently from limited amounts of labeleddata, allowing us to tackle a wider range of Earth observation tasks. Anotherchallenge in this domain is developing algorithms that operate at variablespatial resolutions, e.g., for the problem of classifying land use at differentscales. Recently, self-supervised learning has been applied in the remotesensing domain to exploit readily-available unlabeled data, and was shown toreduce or even close the gap with supervised learning. In this paper, we studyself-supervised visual representation learning through the lens of labelefficiency, for the task of land use classification onmulti-resolution/multi-scale satellite images. We benchmark two contrastiveself-supervised methods adapted from Momentum Contrast (MoCo) and provideevidence that these methods can be perform effectively given little downstreamsupervision, where randomly initialized networks fail to generalize. Moreover,they outperform out-of-domain pretraining alternatives. We use the large-scalefMoW dataset to pretrain and evaluate the networks, and validate ourobservations with transfer to the RESISC45 dataset.

Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery