SUnCNN: Sparse Unmixing Using Unsupervised Convolutional Neural Network

In this letter, we propose a sparse unmixing technique using a convolutional neural network (SUnCNN) for hyperspectral images. SUnCNN is the first deep learning-based technique proposed for sparse unmixing. It uses a deep convolutional encoder-decoder to generate the abundances relying on a spectral library. We reformulate the sparse unmixing into an optimization over the deep network's parameters. Therefore, the deep network learns in an unsupervised manner to map a fixed input into the sparse optimum abundances. Additionally, SUnCNN holds the sum-to-one constraint using a softmax activation layer. The proposed method is compared with the state-of-the-art using two synthetic datasets and one real hyperspectral dataset. The overall results confirm that the proposed method outperforms the other ones in terms of signal to reconstruction error (SRE). Additionally, SUnCNN shows visual superiority for both real and synthetic datasets compared with the competing techniques. The proposed method was implemented in Python (3.8) using PyTorch as the platform for the deep network and is available online: https://github.com/BehnoodRasti/SUnCNN.

Automated summary

The proposed sparse unmixing technique using a convolutional neural network (SUnCNN) for hyperspectral images introduces a new deep learning-based approach that outperforms existing methods in terms of signal to reconstruction error (SRE) and visual presentation on both real and synthetic datasets.