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/

Zendy Plus

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

Zendy Tools

Zendy Open

This work proposes a hybrid unsupervised and supervised learning method topre-train models applied in Earth observation downstream tasks when only ahandful of labels denoting very general semantic concepts are available. Wecombine a contrastive approach to pre-train models with a pixel-wise regressionpre-text task to predict coarse elevation maps, which are commonly availableworldwide. We hypothesize that this will allow the model to pre-learn usefulrepresentations, as there is generally some correlation between elevation mapsand targets in many remote sensing tasks. We assess the performance of ourapproach on a binary semantic segmentation task and a binary imageclassification task, both derived from a dataset created for the northwest ofColombia. In both cases, we pre-train our models with 39k unlabeled images,fine-tune them on the downstream tasks with only 80 labeled images, andevaluate them with 2944 labeled images. Our experiments show that our methods,GLCNet+Elevation for segmentation, and SimCLR+Elevation for classification,outperform their counterparts without the pixel-wise regression pre-text task,namely SimCLR and GLCNet, in terms of macro-average F1 Score and MeanIntersection over Union (MIoU). Our study not only encourages the developmentof pre-training methods that leverage readily available geographicalinformation, such as elevation data, to enhance the performance ofself-supervised methods when applied to Earth observation tasks, but alsopromotes the use of datasets with high-level semantic labels, which are morelikely to be updated frequently. Project code can be found in this link\href{https://github.com/omarcastano/Elevation-Aware-SSL}{https://github.com/omarcastano/Elevation-Aware-SSL}.

Enhancing Self-Supervised Learning for Remote Sensing with Elevation Data: A Case Study with Scarce And High Level Semantic Labels