Three-dimensional Softmax Mechanism Guided Bidirectional GRU Networks for Hyperspectral Remote Sensing Image Classification

Guoqiang Wu, Xin Ning, Luyang Hou, Feng He, Hengmin Zhang, Achyut Shankar

Abstract: Highlights•A new HSI classification model is proposed based on a bidirectional GRU network guided by a three-dimensional Softmax mechanism.•The proposed model leverages the fact that hyperspectral images can be treated as a type of sequence data by introducing bidirectional GRU to process sequences.•The model is evaluated on four widely used hyperspectral datasets, and extensive experiments demonstrate that it is robust.