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

Spectral unmixing has been extensively studied with a variety of methods andused in many applications. Recently, data-driven techniques with deep learningmethods have obtained great attention to spectral unmixing for its superiorlearning ability to automatically learn the structure information. Inparticular, autoencoder based architectures are elaborately designed to solveblind unmixing and model complex nonlinear mixtures. Nevertheless, thesemethods perform unmixing task as blackboxes and lack of interpretability. Onthe other hand, conventional unmixing methods carefully design the regularizerto add explicit information, in which algorithms such as plug-and-play (PnP)strategies utilize off-the-shelf denoisers to plug powerful priors. In thispaper, we propose a generic unmixing framework to integrate the autoencodernetwork with regularization by denoising (RED), named AE-RED. More specially,we decompose the unmixing optimized problem into two subproblems. The first oneis solved using deep autoencoders to implicitly regularize the estimates andmodel the mixture mechanism. The second one leverages the denoiser to bring inthe explicit information. In this way, both the characteristics of the deepautoencoder based unmixing methods and priors provided by denoisers are mergedinto our well-designed framework to enhance the unmixing performance.Experiment results on both synthetic and real data sets show the superiority ofour proposed framework compared with state-of-the-art unmixing approaches.

AE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising