S2IT: Spectral-Spatial Interactive Transformer for Hyperspectral Image Classification

被引：0

作者：

Wang, Minhui ^{[1
,2
]}

Sun, Yaxiu ^{[1
,2
]}

Xiang, Jianhong ^{[1
,2
]}

Zhong, Yu ^{[3
]}

机构：

[1] Harbin Engn Univ, Coll Informat & Commun Engn, Harbin 150001, Peoples R China

[2] Harbin Engn Univ, Key Lab Adv Ship Commun & Informat Technol, Harbin 150001, Peoples R China

[3] Agile & Intelligent Comp Key Lab Sichuan Prov, Chengdu 610000, Peoples R China

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2024年 / 21卷

关键词：

Convolutional neural networks; Sun; Convolutional neural network (CNN); hyperspectral image (HSI); spectral-spatial features; vision transformer (ViT); NETWORK;

D O I：

10.1109/LGRS.2024.3449238

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Hyperspectral image (HSI) encompasses a wealth of spectral-spatial information, offering a sufficient foundation for classification. However, the presence of redundancy poses challenges for achieving accurate classification. In this letter, we design a spectral-spatial interactive transformer (S2IT) for HSI classification (HSIC). S2IT commences with a meticulously designed spectral-spatial reconstruction (S2R) module, which aims to augment the representation of shallow features. Subsequently, an adaptive asymmetric gating mechanism transformer (AGM-Former) aims to delve into and extract comprehensive local-global features from HSI. Ultimately, the spectral-spatial interactive attention (S2IA) synergizes the spectral-spatial features and enhances classification prowess. S2IT demonstrates rigorous experiments on three renowned datasets: Houston2013 (HU), Indian Pines (IP), and the University of Pavia (UP), which validates its effectiveness in enhancing HSIC accuracy.

引用

页数：5

共 20 条

[1] Class-Aligned and Class-Balancing Generative Domain Adaptation for Hyperspectral Image Classification
Feng, Jie
Zhou, Ziyu
Shang, Ronghua
Wu, Jinjian
Zhang, Tianshu
Zhang, Xiangrong
Jiao, Licheng
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 17
[2] Gulati A, 2020, Arxiv, DOI [arXiv:2005.08100, 10.48550/arXiv.2005.08100]
[3] SpectralFormer: Rethinking Hyperspectral Image Classification With Transformers
Hong, Danfeng
Han, Zhu
Yao, Jing
Gao, Lianru
Zhang, Bing
Plaza, Antonio
Chanussot, Jocelyn
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[4] PASSNet: A Spatial-Spectral Feature Extraction Network With Patch Attention Module for Hyperspectral Image Classification
Ji, Renjie
Tan, Kun
Wang, Xue
Pan, Chen
Xin, Liang
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
[5] SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy
Li, Jiafeng
Wen, Ying
He, Lianghua
[J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 6153 - 6162
[6] CNN-Enhanced Graph Convolutional Network With Pixel- and Superpixel-Level Feature Fusion for Hyperspectral Image Classification
Liu, Qichao
Xiao, Liang
Yang, Jingxiang
Wei, Zhihui
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2021, 59 (10): : 8657 - 8671
[7] Hyperspectral Image Classification Using Group-Aware Hierarchical Transformer
Mei, Shaohui
Song, Chao
Ma, Mingyang
Xu, Fulin
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[8] Hyperspectral Image Classification with IFormer Network Feature Extraction
Ren, Qi
Tu, Bing
Liao, Sha
Chen, Siyuan
[J]. REMOTE SENSING, 2022, 14 (19)
[9] Spectral-Spatial Morphological Attention Transformer for Hyperspectral Image Classification
Roy, Swalpa Kumar
Deria, Ankur
Shah, Chiranjibi
Haut, Juan M.
Du, Qian
Plaza, Antonio
[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
[10] HybridSN: Exploring 3-D-2-D CNN Feature Hierarchy for Hyperspectral Image Classification
Roy, Swalpa Kumar
Krishna, Gopal
Dubey, Shiv Ram
Chaudhuri, Bidyut B.
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (02) : 277 - 281

← 1 2 →