Densely Connected Transformer with Frequency Awareness and Sam Guidance for Semi-Supervised Hyperspectral Image Classification

Yutao Rao, Liwei Sun, Junjie Zhang*, Haoran Jiang, Jian Zhang, Dan Zeng

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Advancements in Hyperspectral Image (HSI) spatial resolution pose challenges in pixel-wise classification. Semi-supervised self-training shows potential by using pseudo-labels from unlabeled samples. However, the Hughes phenomenon and environmental factors often lead to spectral variability and undermine pseudo-label credibility. To address above issues, we propose a densely connected Transformer leveraging Discrete Wavelet Transform for extracting nuanced spatial-spectral features and redundancy removal, and we design a filtering strategy guided by the Segment Anything Model (SAM) to retain reliable pseudo labeled samples given the spatial and semantic consistency of HSI regions. Experiments show promising performance of proposed model on high-resolution HSIs compared to trending methods under limited supervision.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Multimedia and Expo, ICME 2024
PublisherIEEE Computer Society
ISBN (Electronic)9798350390155
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event2024 IEEE International Conference on Multimedia and Expo, ICME 2024 - Niagra Falls, Canada
Duration: 15 Jul 202419 Jul 2024

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Conference

Conference2024 IEEE International Conference on Multimedia and Expo, ICME 2024
Country/TerritoryCanada
CityNiagra Falls
Period15/07/2419/07/24

Keywords

  • Discrete Wavelet Transform
  • HSI Classification
  • SAM
  • Semi-Supervised Learning

Fingerprint

Dive into the research topics of 'Densely Connected Transformer with Frequency Awareness and Sam Guidance for Semi-Supervised Hyperspectral Image Classification'. Together they form a unique fingerprint.

Cite this