1 code implementation • 1 Aug 2021 • Haitong Tang, Shuang He, Mengduo Yang, Xia Lu, Qin Yu, Kaiyue Liu, Hongjie Yan, Nizhuan Wang
Through extensive analysis and experiments, we provided credible evidence showing that the multi-layer convolutional sparse coding block enables semantic segmentation model to converge faster, can extract finer semantic and appearance information of images, and improve the ability to recover spatial detail information.
no code implementations • 7 Oct 2021 • Shuang He, Haitong Tang, Xia Lu, Hongjie Yan, Nizhuan Wang
Specifically, our MSHCNet adopted four parallel streams, which contained G-stream, utilizing the irregular correlation between adjacent land covers in terms of first-order graph in non-Euclidean space; C-stream, adopting convolution operator to learn regular spatial-spectral features in Euclidean space; N-stream, combining first and second order features to learn representative and discriminative regular spatial-spectral features of Euclidean space; S-stream, using GSOP to capture boundary correlations and obtain graph representations from all nodes in graphs of non-Euclidean space.