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

In this paper, we introduce a new algorithm based on archetypal analysis forblind hyperspectral unmixing, assuming linear mixing of endmembers. Archetypalanalysis is a natural formulation for this task. This method does not requirethe presence of pure pixels (i.e., pixels containing a single material) butinstead represents endmembers as convex combinations of a few pixels present inthe original hyperspectral image. Our approach leverages an entropic gradientdescent strategy, which (i) provides better solutions for hyperspectralunmixing than traditional archetypal analysis algorithms, and (ii) leads toefficient GPU implementations. Since running a single instance of our algorithmis fast, we also propose an ensembling mechanism along with an appropriatemodel selection procedure that make our method robust to hyper-parameterchoices while keeping the computational complexity reasonable. By using sixstandard real datasets, we show that our approach outperforms state-of-the-artmatrix factorization and recent deep learning methods. We also provide anopen-source PyTorch implementation: https://github.com/inria-thoth/EDAA.

Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing