| Autor: |
Zhang, Lan, Wang, Yang, Yang, Linzi, Chen, Jianfeng, Liu, Zijie, Bian, Lifeng, Yang, Chen |
| Zdroj: |
IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing; 2024, Vol. 17, p2655-2669, 15p |
| Abstrakt: |
Hyperspectral image (HSI) classification has become a popular research topic in recent years, and transformer-based networks have demonstrated superior performance by analyzing global semantic features. However, using transformers for pixel-level HSI classification has two limitations: ineffective capture of spatial-spectral correlations and inadequate exploitation of local features. To address these challenges, we propose a dual-dimension self-attention (D2SA) mechanism that fully exploits HIS's high spectral-spatial correlation by using two separate branches to model the global dependence of features from the spectral and spatial dimensions. Additionally, we develop a multilayer residual convolution module that extracts local features and introduces shallow-deep feature interactions to obtain more discriminative representations. Based on these components, we propose a dual-dimension spectral-spatial bottleneck transformer (D2S2BoT) framework for HSI classification that simultaneously models the local interactions and global dependencies of HSI pixels to achieve high-precision classification. By virtue of the D2SA mechanism, the introduced D2S2BOT framework can produce competitive classification results with a limited number of training samples on three well-known datasets, which we hope will provide a strong baseline for future research on transformers in the field of HSI. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
