WaveFormer: Spectral-Spatial Wavelet Transformer for Hyperspectral Image Classification

被引:44
作者
Ahmad, Muhammad [1 ]
Ghous, Usman [1 ]
Usama, Muhammad [1 ]
Mazzara, Manuel [2 ]
机构
[1] Natl Univ Comp & Emerging Sci, NUCES, Dept Comp Sci, Islamabad 38000, Pakistan
[2] Innopolis Univ, Inst Software Dev & Engn, Innopolis 420500, Russia
关键词
Wavelet transforms; Transformers; Training; Three-dimensional displays; Computational modeling; Hyperspectral imaging; Image classification; Hyperspectral image classification (HSIC); spatial-spectral feature; spatial-spectral transformers (SSTs); wavelet transformer (WaveFormer);
D O I
10.1109/LGRS.2024.3353909
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
Transformers have proven effective for hyperspectral image classification (HSIC) but often incorporate average pooling that results in information loss. This letter presents WaveFormer, a novel transformer-based approach that leverages wavelet transforms for invertible downsampling. This preserves data integrity while enabling attention learning. Specifically, WaveFormer unifies downsampling with wavelet transforms to decompress feature maps without loss. This provides an efficient tradeoff between performance and computation. Furthermore, the wavelet decomposition enhances the interaction between structural and shape information in image patches and channel maps. To evaluate WaveFormer, we conducted extensive experiments on two benchmark hyperspectral datasets. Our results demonstrate that WaveFormer achieves state-of-the-art classification accuracy, obtaining overall accuracies of 95.66% and 96.54% on the Pavia University and the University of Houston datasets, respectively. By integrating wavelet transforms, WaveFormer presents a new transformer architecture for hyperspectral imagery that achieves superior classification without information loss from average pooling.
引用
收藏
页码:1 / 5
页数:5
相关论文
共 29 条
[1]   Hyperspectral Imaging: A Review on UAV-Based Sensors, Data Processing and Applications for Agriculture and Forestry [J].
Adao, Telmo ;
Hruska, Jonas ;
Padua, Luis ;
Bessa, Jose ;
Peres, Emanuel ;
Morais, Raul ;
Sousa, Joaquim Joao .
REMOTE SENSING, 2017, 9 (11)
[2]   Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects [J].
Ahmad, Muhammad ;
Shabbir, Sidrah ;
Roy, Swalpa Kumar ;
Hong, Danfeng ;
Wu, Xin ;
Yao, Jing ;
Khan, Adil Mehmood ;
Mazzara, Manuel ;
Distefano, Salvatore ;
Chanussot, Jocelyn .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 :968-999
[3]   A Fast and Compact 3-D CNN for Hyperspectral Image Classification [J].
Ahmad, Muhammad ;
Khan, Adil Mehmood ;
Mazzara, Manuel ;
Distefano, Salvatore ;
Ali, Mohsin ;
Sarfraz, Muhammad Shahzad .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
[4]  
Bedini E, 2017, Journal of Hyperspectral Remote Sensing, V7, P189, DOI [10.29150/jhrs.v7.4.p189-211, 10.29150/jhrs.v7.4.p189-211, DOI 10.29150/JHRS.V7.4.P189-211]
[5]   Real-time processing algorithms for target detection and classification in hyperspectral imagery [J].
Chang, CI ;
Ren, H ;
Chiang, SS .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2001, 39 (04) :760-768
[6]  
Dosovitskiy A, 2021, Arxiv, DOI arXiv:2010.11929
[7]   Hybrid 3D/2D Complete Inception Module and Convolutional Neural Network for Hyperspectral Remote Sensing Image Classification [J].
Firat, Huseyin ;
Asker, Mehmet Emin ;
Bayindir, Mehmet Ilyas ;
Hanbay, Davut .
NEURAL PROCESSING LETTERS, 2023, 55 (02) :1087-1130
[8]  
Fujieda S, 2018, Arxiv, DOI [arXiv:1805.08620, DOI 10.48550/ARXIV.1805.08620]
[9]   Hyperspectral Image Classification Using a Hybrid 3D-2D Convolutional Neural Networks [J].
Ghaderizadeh, Saeed ;
Abbasi-Moghadam, Dariush ;
Sharifi, Alireza ;
Zhao, Na ;
Tariq, Aqil .
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 (14) :7570-7588
[10]   A Survey on Vision Transformer [J].
Han, Kai ;
Wang, Yunhe ;
Chen, Hanting ;
Chen, Xinghao ;
Guo, Jianyuan ;
Liu, Zhenhua ;
Tang, Yehui ;
Xiao, An ;
Xu, Chunjing ;
Xu, Yixing ;
Yang, Zhaohui ;
Zhang, Yiman ;
Tao, Dacheng .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (01) :87-110