An Attention-Based Lattice Network for Hyperspectral Image Classification

No Thumbnail Available
File version
Author(s)
Nikzad, Mohammad
Gao, Yongsheng
Zhou, Jun
Primary Supervisor
Other Supervisors
Editor(s)
Date
2022
Size
File type(s)
Location
License
Abstract

Convolutional neural networks (CNNs) with 3-D convolutional kernels are widely used for hyperspectral image (HSI) classification, which bring notable benefits in capturing joint spectral and spatial features. However, they suffer from poor computational efficiency, causing the low training/inference speed of the model. On the contrary, CNN-based methods with 1-D and 2-D kernels are efficient but mostly restricted to extracting either spectral or spatial features. Moreover, most CNN-based HSI classification frameworks are incapable of simultaneously taking advantage of residual and dense aggregations without over-allocating parameters or information loss for feature reusage. This article presents a novel attention-based lattice network (ALN) to overcome these shortcomings. The proposed 2-D lattice framework can effectively harness the advantages of residual and dense aggregations to achieve outstanding accuracy performance and computational efficiency simultaneously. Furthermore, the ALN employs a unique joint spectral-spatial attention mechanism to capture both spectral and spatial information effectively. In particular, a new pointwise spectral attention mechanism is adopted to fully capture spectral dependences for every pixel. Our extensive experimental investigation verifies the effectiveness and efficiency of the ALN architecture for HSI classification.

Journal Title
IEEE Transactions on Geoscience and Remote Sensing
Conference Title
Book Title
Edition
Volume
60
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject
Earth sciences
Engineering
Science & Technology
Physical Sciences
Technology
Geochemistry & Geophysics
Engineering, Electrical & Electronic
Persistent link to this record
Citation
Nikzad, M; Gao, Y; Zhou, J, An Attention-Based Lattice Network for Hyperspectral Image Classification, IEEE Transactions on Geoscience and Remote Sensing, 2022, 60, pp. 5526215
Collections