• Home
  • Search
  • Spectral–Spatial Masked Transformer With Supervised and Contrastive Learning for Hyperspectral Image Classification
  • Cite Icon77
  • https://doi.org/10.1109/tgrs.2023.3264235Copy DOI Icon

Spectral–Spatial Masked Transformer With Supervised and Contrastive Learning for Hyperspectral Image Classification

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

Recently, due to the powerful capability at modeling the long-range relationships, Transformer-based methods have been widely explored in many research areas including hyperspectral image (HSI) classification. However, because of lots of trainable parameters and the lack of inductive bias, it is difficult to train a Transformer-based HSI classifier, especially when the number of training samples is limited. To address this issue, in this study, spectral-spatial masked Transformer (SS-MTr) is explored for HSI classification, which uses a two-stage training strategy. In the first stage, SS-MTr pre-trains a vanilla Transformer via reconstruction from masked HSI inputs, which embeds the local inductive bias into the Transformer. In the second stage, the well pre-trained Transformer is cooperated with a fully connected layer and then fine-tuned for the HSI classification. Furthermore, in order to incorporate discriminative feature learning into the SS-MTr, three SS-MTr-based methods, including contrastive SS-MTr (C-SS-MTr), supervised SS-MTr (S-SS-MTr), and supervised contrastive SS-MTr (SC-SS-MTr) are proposed by adding extra branches for specific tasks in parallel with the existing reconstruction task. Specifically, the proposed C-SS-MTr adds a contrastive loss which brings instance discriminability. Besides, the proposed S-SS-MTr builds an extra classification branch for embracing inter-class discriminability and intra-class similarity. Moreover, the proposed SC-SS-MTr combines C-SS-MTr and S-SS-MTr for better generalization. The proposed SS-MTr, C-SS-MTr, S-SS-MTr, and SC-SS-MTr are tested on three popular hyperspectral datasets (i.e., Indian Pines, Pavia University, and Houston). The obtained results reveal that the proposed models achieve competitive results compared with the state-of-the-art HSI classification methods. Code is available at https://github.com/mengduanjinghua/SS-MTr.

Similar Papers
  • Research Article
  • Citations1

Multi-Scale Adaptive Diffusion Feature Fusion with Causal Invariance Learning for Hyperspectral Image Classification

  • May 01, 2025
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Wanxing Zha +7
  • Research Article
  • Citations69

Heterogeneous Few-Shot Learning for Hyperspectral Image Classification

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Yan Wang +7
  • PDF
  • Research Article
  • Citations42

A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification.

  • Mar 03, 2021
  • Sensors
  • Xiang Hu +4
  • PDF
  • Research Article
  • Citations14

Small Sample Hyperspectral Image Classification Method Based on Dual-Channel Spectral Enhancement Network

  • Aug 13, 2022
  • Electronics
  • Songwei Pei +2
  • PDF
  • Research Article
  • Citations16

Pyramidal Dilation Attention Convolutional Network With Active and Self-Paced Learning for Hyperspectral Image Classification

  • Jan 01, 2023
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Wenhui Hou +4
  • PDF
  • Research Article
  • Citations1

Attention 3D central difference convolutional dense network for hyperspectral image classification

  • Apr 10, 2024
  • PLOS ONE
  • Mahmood Ashraf +9
  • PDF
  • Research Article
  • Citations11

Attention 3D central difference convolutional dense network for hyperspectral image classification.

  • Apr 10, 2024
  • PloS one
  • Mahmood Ashraf +5
  • Conference Article
  • Citations1

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

  • Sep 22, 2023
  • Yubing Wang +2
  • Research Article
  • Citations8

HyperGCN – a multi-layer multi-exit graph neural network to enhance hyperspectral image classification

  • Jul 05, 2024
  • International Journal of Remote Sensing
  • Haseena Rahmath P +3
  • PDF
  • Research Article
  • Citations11

A 3D-2D Convolutional Neural Network and Transfer Learning for Hyperspectral Image Classification

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Douglas Omwenga Nyabuga +3
  • PDF
  • Research Article
  • Citations11

An Encoder–Decoder Convolution Network With Fine-Grained Spatial Information for Hyperspectral Images Classification

  • Jan 01, 2020
  • IEEE Access
  • Zhongwei Li +4
  • Research Article
  • Citations185

Heterogeneous Transfer Learning for Hyperspectral Image Classification Based on Convolutional Neural Network

  • Dec 05, 2019
  • IEEE Transactions on Geoscience and Remote Sensing
  • Xin He +2
  • PDF
  • Research Article
  • Citations10

Hyperspectral Image Classification Based on Sparse Superpixel Graph

  • Sep 09, 2021
  • Remote Sensing
  • Yifei Zhao +1
  • Conference Article
  • Citations8

Heterogeneous Few-shot Learning with Knowledge Distillation for Hyperspectral Image Classification

  • Jan 14, 2022
  • Yanfang Hu +3
  • PDF
  • Research Article
  • Citations24

Combining Spectral Unmixing and 3D/2D Dense Networks with Early-Exiting Strategy for Hyperspectral Image Classification

  • Feb 29, 2020
  • Remote Sensing
  • Bei Fang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.