Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 34, Issue 11, Pages 8989-9003Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3155114
Keywords
Feature extraction; Data mining; Convolutional neural networks; Atomic measurements; Hyperspectral imaging; Transformers; Spectral analysis; Central attention; hyperspectral imagery (HSI); spectral-spatial feature extraction; transformer
Ask authors/readers for more resources
This article analyzes the intrinsic properties of hyperspectral imagery (HSI) and builds two principles for spectral-spatial feature extraction. The proposed SDPCA algorithm and CAN network can extract spectral-spatial information from the central pixel and similar pixels. Experimental results demonstrate the superior classification performance of CAN and MiniCAN compared to other methods.
In this article, the intrinsic properties of hyperspectral imagery (HSI) are analyzed, and two principles for spectral-spatial feature extraction of HSI are built, including the foundation of pixel-level HSI classification and the definition of spatial information. Based on the two principles, scaled dot-product central attention (SDPCA) tailored for HSI is designed to extract spectral-spatial information from a central pixel (i.e., a query pixel to be classified) and pixels that are similar to the central pixel on an HSI patch. Then, employed with the HSI-tailored SDPCA module, a central attention network (CAN) is proposed by combining HSI-tailored dense connections of the features of the hidden layers and the spectral information of the query pixel. MiniCAN as a simplified version of CAN is also investigated. Superior classification performance of CAN and miniCAN on three datasets of different scenarios demonstrates their effectiveness and benefits compared with state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available