S2Former: Parallel Spectral–Spatial Transformer for Hyperspectral Image Classification

S2Former: Parallel Spectral–Spatial Transformer for Hyperspectral Image Classification

Due to their excellent representation talent in local features, the convolutional neural network (CNN) has achieved favourable performance in hyperspectral image (HSI) classification tasks. Nevertheless, current CNN models exhibit a marked flaw: they are hard to model the dependencies in long-range...

Full description

Bibliographic Details
Main Authors: Dong Yuan, Dabing Yu, Yixi Qian, Yongbing Xu, Yan Liu
Format: Article
Language:English
Published: MDPI AG 2023-09-01
Series:Electronics
Subjects:
transformer
hyperspectral image (HSI) classification
multi-head covariance spectral attention (MCSA)
multi-head spatial self-attention (MSSA)
local activation feed-forward network (LAFN)
Online Access:https://www.mdpi.com/2079-9292/12/18/3937

Internet

https://www.mdpi.com/2079-9292/12/18/3937

Similar Items