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 development of semi-supervised learning techniques is essential toenhance the generalization capacities of machine learning algorithms. Indeed,raw image data are abundant while labels are scarce, therefore it is crucial toleverage unlabeled inputs to build better models. The availability of largedatabases have been key for the development of learning algorithms with highlevel performance.  Despite the major role of machine learning in Earth Observation to deriveproducts such as land cover maps, datasets in the field are still limited,either because of modest surface coverage, lack of variety of scenes orrestricted classes to identify. We introduce a novel large-scale dataset forsemi-supervised semantic segmentation in Earth Observation, the MiniFrancesuite. MiniFrance has several unprecedented properties: it is large-scale,containing over 2000 very high resolution aerial images, accounting for morethan 200 billions samples (pixels); it is varied, covering 16 conurbations inFrance, with various climates, different landscapes, and urban as well ascountryside scenes; and it is challenging, considering land use classes withhigh-level semantics. Nevertheless, the most distinctive quality of MiniFranceis being the only dataset in the field especially designed for semi-supervisedlearning: it contains labeled and unlabeled images in its training partition,which reproduces a life-like scenario. Along with this dataset, we presenttools for data representativeness analysis in terms of appearance similarityand a thorough study of MiniFrance data, demonstrating that it is suitable forlearning and generalizes well in a semi-supervised setting. Finally, we presentsemi-supervised deep architectures based on multi-task learning and the firstexperiments on MiniFrance.

Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study