AssociativeFormer: Integrating Sparse Memory Attention and Versatile Tokenization for Hyperspectral Image Classification

Developing hyperspectral image classification models has long been hindered by problems regarding spectral redundancy and complexity, as well as the limitations of previously proposed transformer methods. We present <italic>AssociativeFormer</italic>, an architecture designed to address hyperspectra...

Descrición completa

Detalles Bibliográficos

Principais autores:	Ayesha Shafique, Mohammad Siraj, Saad Sohail, Saif A. Alsaif, Benmao Cheng
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2026-01-01
Series:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Assuntos:	Associative memory hyperspectral image classification remote sensing sparse attention spatial-spectral tokenization transformer networks
Acceso en liña:	https://ieeexplore.ieee.org/document/11481669/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!