Hyperspectral Image Classification Based on Multi-stage Vision Transformer with Stacked Samples

研究成果: Conference contribution

抄録

Hyperspectral image classification (HSIC) is a task assigning the correct label to each pixel. It is a hot topic in the remote sensing field, which has been processed in several deep learning methods. Recently, there are some works that apply Vision Transformer (ViT) methods to the HSIC task, but the performance is not as good as some CNN-structured methods, considering that Vision Transformer uses attention to capture global information but ignores local characteristics. In this paper, a multi-stage Vision Transformer model referring to the feature extraction structure of CNN is proposed, and the result shows the realizability and reliability. Besides, experiments show that the modified ViT structure needs more samples for training. An innovative data augmentation method is used to generate extended samples with virtual yet reliable labels. The generated samples are combined with the original ones as the stacked samples, which are used for the following feature extraction process. Experiments explain the optimization of the multi-stage Vision Transformer structure with stacked samples in the accuracy term compared with other methods.

本文言語English
ホスト出版物のタイトルTENCON 2021 - 2021 IEEE Region 10 Conference
出版社Institute of Electrical and Electronics Engineers Inc.
ページ441-446
ページ数6
ISBN(電子版)9781665495325
DOI
出版ステータスPublished - 2021
イベント2021 IEEE Region 10 Conference, TENCON 2021 - Auckland, New Zealand
継続期間: 2021 12月 72021 12月 10

出版物シリーズ

名前IEEE Region 10 Annual International Conference, Proceedings/TENCON
2021-December
ISSN(印刷版)2159-3442
ISSN(電子版)2159-3450

Conference

Conference2021 IEEE Region 10 Conference, TENCON 2021
国/地域New Zealand
CityAuckland
Period21/12/721/12/10

ASJC Scopus subject areas

  • コンピュータ サイエンスの応用
  • 電子工学および電気工学

フィンガープリント

「Hyperspectral Image Classification Based on Multi-stage Vision Transformer with Stacked Samples」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル