Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixing

TL;DR

This paper presents a novel archetypal analysis algorithm using entropic gradient descent for blind hyperspectral unmixing, which outperforms existing methods and is efficiently implementable on GPUs.

Contribution

Introduces a new entropic gradient descent-based archetypal analysis method for hyperspectral unmixing that does not require pure pixels and is robust with an ensembling approach.

Findings

Outperforms state-of-the-art matrix factorization methods

Achieves better solutions than traditional archetypal analysis

Enables efficient GPU implementation

Abstract

In this paper, we introduce a new algorithm based on archetypal analysis for blind hyperspectral unmixing, assuming linear mixing of endmembers. Archetypal analysis is a natural formulation for this task. This method does not require the presence of pure pixels (i.e., pixels containing a single material) but instead represents endmembers as convex combinations of a few pixels present in the original hyperspectral image. Our approach leverages an entropic gradient descent strategy, which (i) provides better solutions for hyperspectral unmixing than traditional archetypal analysis algorithms, and (ii) leads to efficient GPU implementations. Since running a single instance of our algorithm is fast, we also propose an ensembling mechanism along with an appropriate model selection procedure that make our method robust to hyper-parameter choices while keeping the computational complexity reasonable. By using six standard real datasets, we show that our approach outperforms state-of-the-art matrix factorization and recent deep learning methods. We also provide an open-source PyTorch implementation: https://github.com/inria-thoth/EDAA.