Transformer-Enhanced CNN Based on Intensive Feature for Hyperspectral Unmixing

Benefitting from superior performance of learning a low-dimensional sparse representation, autoencoders (AEs) are widely applied to hyperspectral unmixing (HU) task, which aims at identifying and quantifying material components in hyperspectral pixels. In this letter, we propose an innovative AE named Transformer-enhanced convolutional neural network (CNN) based on intensive feature (
TCN
) to improve the performance of HU. Specifically, the
TCN
is based on a spatial-spectral decomposition fusion mechanism and integrates the local modeling capability of CNN with the global context modeling capability of Transformer. Our
TCN
consists of the spectral Swin Transformer block (SSTB), spatial convolutional block (SCB), and the intensive feature fusion block (IFFB). First, the SSTB considers the global spectral context, while the SCB is utilized to extract local spatial features. Then, the IFFB achieves effective integration and complementarity of features from different sources and fully utilizes the intensive features to improve the accuracy and stability of the
TCN
. Experiments on the dataset demonstrate that the performance of our proposed method significantly outperforms other HU methods.