• Home
  • Search
  • BS2T: Bottleneck Spatial–Spectral Transformer for Hyperspectral Image Classification
  • Cite Icon84
  • https://doi.org/10.1109/tgrs.2022.3185640Copy DOI Icon

BS2T: Bottleneck Spatial–Spectral Transformer for Hyperspectral Image Classification

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Convolutional Neural Networks (CNNs) have been extensively applied to hyperspectral (HS) image classification tasks and achieved promising performance. However, for CNN based HS image classification methods, it is hard to depict the dependencies among HS image pixels in long-range distanced positions and bands. Moreover, the limited receptive field of the convolutional layers extremely hinders the development of the CNN structure. To tackle these problems, in this paper, the novel Bottleneck Spatial-Spectral Transformer (BS2T) is proposed to depict the long-range global dependencies of HS image pixels, which can be regarded as a feature extraction module for HS image classification networks. More specifically, inspired by Bottleneck Transformer in computer vision, for HS image feature extraction, the proposed BS2T is incorporated with a feature contraction module, a multi-head spatial-spectral self-attention (MHS2A) module and a feature expansion module. In this way, convolutional operations are replaced by the MHS2A to capture the long-range dependency of HS pixels regardless of their spatial position and distance. Meanwhile, in the MHS2A module, to highlight the spectral features of HS images, we introduce the spectral information and content spatial positional information to classical multi-head self-attentions to make the attentions more positional aware and spectral aware. On this basis, a dual-branch HS image classification framework based on 3D CNN and BS2T is defined for jointly extracting the local-global features of HS images. Experimental results on three public HS image classification datasets show that the proposed classification framework achieves a significant improvement when comparing with the state-of-the-art methods. The source code of the proposed framework can be downloaded from https://github.com/srxlnnu/BS2T.

Similar Papers
  • Research Article
  • Citations1

3DVT: Hyperspectral Image Classification Using 3D Dilated Convolution and Mean Transformer

  • Feb 11, 2025
  • Photonics
  • Xinling Su +1
  • Conference Article
  • Citations1

Lightweight Multilevel Feature Fusion Network for Hyperspectral Image Classification

  • Nov 26, 2022
  • Quanyu Huang +3
  • Research Article
  • Citations37

Advances in Hyperspectral Image Classification Based on Convolutional Neural Networks: A Review

  • Jan 01, 2022
  • Computer Modeling in Engineering & Sciences
  • Somenath Bera +2
  • Research Article
  • Citations7

Hybrid spatial-spectral generative adversarial network for hyperspectral image classification.

  • Feb 21, 2023
  • Journal of the Optical Society of America A
  • Chao Ma +5
  • Research Article
  • Citations345

Hyperspectral Image Classification Using Group-Aware Hierarchical Transformer

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Shaohui Mei +3
  • Conference Article
  • Citations1

Hyperspectral Image Classification Using 3D Attention Mechanism in Collaboration with Transformer

  • Sep 22, 2023
  • Yubing Wang +2
  • Research Article
  • Citations31

State space models meet transformers for hyperspectral image classification

  • Aug 22, 2024
  • Signal Processing
  • Xuefei Shi +6
  • Conference Article
  • Citations5

A Deep Learning approach to Hyperspectral Image Classification using an improved Hybrid 3D-2D Convolutional Neural Network

  • Sep 02, 2020
  • Dimitra Koumoutsou +1
  • Conference Article
  • Citations9

Hyperspectral Image Classification Using Hierarchical Spatial-Spectral Transformer

  • Jul 17, 2022
  • Chao Song +5
  • Research Article
  • Citations13

Multi-granularity vision transformer via semantic token for hyperspectral image classification

  • Sep 02, 2022
  • International Journal of Remote Sensing
  • Bin Li +5
  • Research Article
  • Citations3

Dual-input ultralight multi-head self-attention learning network for hyperspectral image classification

  • Feb 02, 2024
  • International Journal of Remote Sensing
  • Xinhao Li +4
  • Conference Article
  • Citations1

Hyperspectral Image Classification Based on Convolutional Neural Networks With Adaptive Network Structure

  • Oct 01, 2018
  • Chen Ding +5
  • PDF
  • Research Article
  • Citations62

FusionNet: A Convolution–Transformer Fusion Network for Hyperspectral Image Classification

  • Aug 19, 2022
  • Remote Sensing
  • Liming Yang +6
  • Research Article
  • Citations3

A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.

  • May 23, 2025
  • PloS one
  • Yuping Yin +2
  • Research Article
  • Citations36

Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xizhe Xue +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.