Deep Interpretable Fully CNN Structure for Sparse Hyperspectral Unmixing via Model-Driven and Data-Driven Integration

Hyperspectral unmixing (HSU), which aims to identify constituent materials and estimate the corresponding proportions in a scene, is an essential research topic in remote sensing. Most deep learning-based methods are data-inspired, relying on massive amounts of data to train black-box-like networks, while a few model-inspired unmixing networks only consider the spectral features of the pixel, ignoring the exploration of spatial information between pixels. In this article, we design a network topology according to the classical iterative algorithm, and the large number of learnable parameters contained in the network is continuously updated through data fitting. In other words, we integrate the concepts of both model- and data-driven and propose a deep interpretable fully convolutional neural network (DIFCNN). The iteration of the classic sparse unmixing algorithm is unfolded to provide guidance for the network structure and incorporate prior knowledge into the network. Meanwhile, 2-D convolutional layers are employed to automatically learn the spatial information at different scales. A known spectral library is used as a prior to initialize network parameters and reconstruct the image. The DIFCNN adopts an end-to-end training strategy; in addition, we establish a new loss function that adds a joint sparse constraint on the abundance result to the cross-entropy loss. Experiments on both synthetic and real datasets show that the performance of the DIFCNN not only outperforms the sparse unmixing by variable splitting and augmented Lagrangian (SUnSAL) and its improved algorithms but also is highly competitive in the state-of-the-art methods of deep learning.