Residual Spatial Attention Kernel Generation Network for Hyperspectral Image Classification With Small Sample Size

Xu, Yanbing; Zhang, Yanmei; Yu, Chengcheng; Ji, Chao; Yue, Tingxuan; Li, Huan

doi:10.1109/tgrs.2022.3175494

Cited by 6 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gao et al, 2021;Kang et al, 2019;C. Wu et al, 2019;Xu et al, 2022;Zhixiang Xue et al, 2022;Zuo et al, 2020) used the same hyperspectral images (HSIs) from a dataset held by the Italian University of Pavia. Some of these authors compared these HSIs with other available HSI datasets: Salinas six papers (Ding et al, 2022;K.…”

Section: Variousmentioning

confidence: 99%

See 1 more Smart Citation

Ten deep learning techniques to address small data problems with remote sensing

Safonova¹,

Ghazaryan²,

Stiller³

et al. 2023

Preprint

View full text Add to dashboard Cite

Researchers and engineers have increasingly used Deep Learning (DL) for a variety of Remote Sensing (RS) tasks. However, data from local observations or via ground truth is often quite limited for training DL models, especially when these models represent key socio-environmental problems, such as the monitoring of extreme, destructive climate events, biodiversity, and sudden changes in ecosystem states. Such cases, also known as small data problems, pose significant methodological challenges. This review summarises these challenges in the RS domain and the possibility of using emerging DL techniques to overcome them. We show that the small data problem is a common challenge across disciplines and scales that results in poor model generalisability and transferability, yet this has not been investigated in a structured way. We first introduce ten emerging DL techniques: transfer learning, self-supervised learning, semi-supervised learning, few-shot learning, zero-shot learning, active learning, weakly supervised learning, multitask learning, process-aware learning, and ensemble learning; we also include a validation technique known as spatial k-fold cross validation. These techniques have shown promising potential in other scientific disciplines, but have been rarely applied in the RS domain. We also provide guidance on which learning technique to use in various cases, which helps to create a more methodologically robust DL application (and a greater number of them) that can be used to tackle socially important problems with limited data.

show abstract

Section: Variousmentioning

confidence: 99%

“…Feng et al, 2022;Kang et al, 2019;C. Wu et al, 2019;Xu et al, 2022), Kennedy Space Centertwo papers (H. Xu et al, 2022), and Houstontwo papers (F. Zhixiang Xue et al, 2022).…”

Section: Variousmentioning

confidence: 99%