Global-Local Channel Attention for Hyperspectral Image Classification

Peilin Yan, Haolin Qin, Jihui Wang, Tingfa Xu, Liqiang Song, Hui Li, Jianan Li

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

1 Citation (Scopus)

Abstract

Hyperspectral image classification (HSIC) assigns a pixel-wise semantic label leveraging the rich information in the broad spectral band. However, most of the existent HSIC algorithm fail to take advantage of varying importance of different channels, which hinder the further improve of the performance. To this end, we originally propose a Global-Local Channel Attention (GLCA) module to assist the process of selecting useful channels while suppressing others. Working in a plug-and-play fashion, GLCA precisely re-calibrate channel-wise feature responses in a pixel-wise manner, flexible enough to be applied to any existing depth-based HSIC model with little additional computational cost. Rich experiments prove the effectiveness of our algorithm, and to the best of our knowledge, we establish new state-of-the-arts on multiple HSIC datasets.

Original languageEnglish
Title of host publicationInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665442312
DOIs
Publication statusPublished - 2021
Event2021 International Conference on Electrical, Computer, and Energy Technologies, ICECET 2021 - Cape Town, South Africa
Duration: 9 Dec 202110 Dec 2021

Publication series

NameInternational Conference on Electrical, Computer, and Energy Technologies, ICECET 2021

Conference

Conference2021 International Conference on Electrical, Computer, and Energy Technologies, ICECET 2021
Country/TerritorySouth Africa
CityCape Town
Period9/12/2110/12/21

Keywords

  • channel at-tention
  • global-local feature
  • hyperspectral image classification
  • pixel-wise

Fingerprint

Dive into the research topics of 'Global-Local Channel Attention for Hyperspectral Image Classification'. Together they form a unique fingerprint.

Cite this