SpACNN-LDVAE: Spatial Attention Convolutional Latent Dirichlet Variational Autoencoder for Hyperspectral Pixel Unmixing
This work addresses hyperspectral image analysis for remote sensing applications, presenting an incremental improvement over existing methods.
The paper tackled hyperspectral pixel unmixing by extending a Latent Dirichlet Variational Autoencoder to incorporate local spatial context, resulting in improved endmember extraction and abundance estimation across multiple datasets.
The hyperspectral pixel unmixing aims to find the underlying materials (endmembers) and their proportions (abundances) in pixels of a hyperspectral image. This work extends the Latent Dirichlet Variational Autoencoder (LDVAE) pixel unmixing scheme by taking into account local spatial context while performing pixel unmixing. The proposed method uses an isotropic convolutional neural network with spatial attention to encode pixels as a dirichlet distribution over endmembers. We have evaluated our model on Samson, Hydice Urban, Cuprite, and OnTech-HSI-Syn-21 datasets. Our model also leverages the transfer learning paradigm for Cuprite Dataset, where we train the model on synthetic data and evaluate it on the real-world data. The results suggest that incorporating spatial context improves both endmember extraction and abundance estimation.