Efficient Hyperspectral Imagery Classification Method with Lightweight Structure and Image Transformation-Based Data Augmentation

Denis Ivanitsa, Wei Wei

科研成果: 书/报告/会议事项章节会议稿件同行评审

5 引用 (Scopus)

摘要

With the increasing popularity of deep learning models in the hyperspectral image (HSI) classification field, more and more complex methods have been proposed. However, an increase in accuracy was accompanied by an increase in model size and computational complexity. As a result, application of these models will be limited in solutions with strict hardware specifications, as well as solutions with a limited training set. To reduce the required number of parameters and total FLOPs, we design a lightweight model for HSI classification, based on a ghost module. Specifically, we use 3D ghost modules to build an efficient 3D-CNN network termed TinyNet. To further increase the performance of our TinyNet model, a combination of cross-entropy and contrastive center loss is utilized for training. Additionally, we design a novel augmentation technique based on image transformations. The proposed lightweight model, together with our augmentation technique, can lead to satisfactory HSI classification results. Experimental results on two HSI datasets demonstrate the effectiveness of the proposed HSI classification method when compared to the competing techniques.

源语言英语
主期刊名IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
出版商Institute of Electrical and Electronics Engineers Inc.
3560-3563
页数4
ISBN(电子版)9781665427920
DOI
出版状态已出版 - 2022
活动2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, 马来西亚
期限: 17 7月 202222 7月 2022

出版系列

姓名International Geoscience and Remote Sensing Symposium (IGARSS)
2022-July

会议

会议2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
国家/地区马来西亚
Kuala Lumpur
时期17/07/2222/07/22

指纹

探究 'Efficient Hyperspectral Imagery Classification Method with Lightweight Structure and Image Transformation-Based Data Augmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此