An efficient Transformer with neighborhood contrastive tokenization for hyperspectral images classification

The success of vision Transformers (ViTs) relies heavily on the self-attention mechanism, which requires support from appropriate patch tokenization. However, hyperspectral image (HSI) often suffer from significant noise distortions and spectral uncertainty, which result in unstable attention patter...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Miaomiao Liang, Xianhao Zhang, Xiangchun Yu, Lingjuan Yu, Zhe Meng, Xiaohong Zhang, Licheng Jiao
Format:	Artigo
Sprog:	Inglês
Udgivet:	Elsevier 2024-07-01
Serier:	International Journal of Applied Earth Observations and Geoinformation
Fag:	Hyperspectral image (HSI) Transformer Contrastive tokenization Self-supervised learning (SSL)
Online adgang:	http://www.sciencedirect.com/science/article/pii/S1569843224003339
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!