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

Airborne hyperspectral images can be used to map the land cover in largeurban areas, thanks to their very high spatial and spectral resolutions on awide spectral domain. While the spectral dimension of hyperspectral images ishighly informative of the chemical composition of the land surface, the use ofstate-of-the-art machine learning algorithms to map the land cover has beendramatically limited by the availability of training data. To cope with thescarcity of annotations, semi-supervised and self-supervised techniques havelately raised a lot of interest in the community. Yet, the publicly availablehyperspectral data sets commonly used to benchmark machine learning models arenot totally suited to evaluate their generalization performances due to one orseveral of the following properties: a limited geographical coverage (whichdoes not reflect the spectral diversity in metropolitan areas), a small numberof land cover classes and a lack of appropriate standard train / test splitsfor semi-supervised and self-supervised learning. Therefore, we release in thispaper the Toulouse Hyperspectral Data Set that stands out from other data setsin the above-mentioned respects in order to meet key issues in spectralrepresentation learning and classification over large-scale hyperspectralimages with very few labeled pixels. Besides, we discuss and experiment theself-supervised task of Masked Autoencoders and establish a baseline forpixel-wise classification based on a conventional autoencoder combined with aRandom Forest classifier achieving 82% overall accuracy and 74% F1 score. TheToulouse Hyperspectral Data Set and our code are publicly available athttps://www.toulouse-hyperspectral-data-set.com andhttps://www.github.com/Romain3Ch216/tlse-experiments, respectively.

Toulouse Hyperspectral Data Set: a benchmark data set to assess  semi-supervised spectral representation learning and pixel-wise  classification techniques