Slide Fifth
Slide Second
Slide Fourth
Slide Sixth
Slide Sixth
International Geoscience and Remote Sensing Symposium

In 2021 a joint initiative of Belgium and The Netherlands

TU2.MM-9.5

ENSEMBLE CNN WITH ENHANCED FEATURE SUBSPACES FOR IMBALANCED HYPERSPECTRAL IMAGE CLASSIFICATION

Qinzhe Lv, Wei Feng, Yinghui Quan, Xidian University, China; Qiang Li, Northwestern Polytechnical University, China; Gabriel Dauphin, University Paris XIII, France; Lianru Gao, Chinese Academy of Sciences, China; Guoping Zhao, Shaan Xi Academy of Forestry, China; Mengdao Xing, Xidian University, China
Session:
Deep Learning for Hyperspectral Image Classification II
Track:
Data Analysis Methods (Optical, Multispectral,Hyperspectral, SAR)
Presentation Time:
Tue, 13 Jul, 11:20-11:25 (UTC)
Tue, 13 Jul, 13:20-13:25 Central Europe Summer Time (UTC +2)
Tue, 13 Jul, 19:20-19:25 China Standard Time (UTC +8)
Tue, 13 Jul, 07:20-07:25 Eastern Daylight Time (UTC -4)
Session Co-Chairs:
Wei Wei, Northwestern Polytechnical University and Feng Shou, College of Information and Communication Engineering, Harbin Engineering University
Session Manager:
Thimm Zwiener
Presentation
Discussion
Resources
Session TU2.MM-9
TU2.MM-9.1: HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON DENSE CONVOLUTION AND CONDITIONAL RANDOM FIELD
Chunhui Zhao, Harbin University of Engineering, China; Boao Qin, Tong Li, Shou Feng, Yiming Yan, Harbin Engineering University, China
TU2.MM-9.2: MIRROR MOSAICKING BASED REDUCED COMPLEXITY APPROACH FOR THE CLASSIFICATION OF HYPERSPECTRAL IMAGES
S N Chaudhri, Naveen Singh Rajput, K P Singh, IIT(BHU), India; Dharmendra Singh, IIT, Roorkee, INDIA, India
TU2.MM-9.3: HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON SPECTRAL GRAPH AND BIDIRECTIONAL LSTM NETWORK
Xu Tang, Qionglin Zhou, Fanbo Meng, Xidian University, China; Xiao Han, Geovis Spatial Technology Co.,Ltd, China; Dalei Li, Science and Technology on Electro-optic Control Laboratory, China; Xiangrong Zhang, Licheng Jiao, Xidian University, China
TU2.MM-9.4: Deep Diffusion Processes for Active Learning of Hyperspectral Images
Abiy Tasissa, Tufts University, United States; Duc Nguyen, University of Maryland, United States; James Murphy, Tufts University, United States
TU2.MM-9.5: ENSEMBLE CNN WITH ENHANCED FEATURE SUBSPACES FOR IMBALANCED HYPERSPECTRAL IMAGE CLASSIFICATION
Qinzhe Lv, Wei Feng, Yinghui Quan, Xidian University, China; Qiang Li, Northwestern Polytechnical University, China; Gabriel Dauphin, University Paris XIII, France; Lianru Gao, Chinese Academy of Sciences, China; Guoping Zhao, Shaan Xi Academy of Forestry, China; Mengdao Xing, Xidian University, China
TU2.MM-9.6: Boosting CNN for Hyperspectral Image Classification
Haoyu Zhang, Yushi Chen, Xin He, Harbin Institute of Technology, China; Xingliang Shen, Tianjin Navigation Instruments Research Institute, China
TU2.MM-9.7: HSGACN: HYPERSPECTRAL IMAGE CLASSIFICATION ALGORITHM BASED ON GRAPH CONVOLUTIONAL NETWORK
Yi Xiao, Siying Chen, Hao Wang, Zhengang Zhao, Tao Huang, Yuchen Liang, Jin Qin, Rong Ma, Zongyao Yin, Ruiqing Yan, Xianchuan Yu, Beijing Normal University, China
TU2.MM-9.8: META TRANSFER LEARNING FOR FEW-SHOT HYPERSPECTRAL IMAGE CLASSIFICATION
Fei Zhou, Lei Zhang, Wei Wei, Northwestern Polytechnical University, China; Zongwen Bai, Yanan University, China; Yanning Zhang, Northwestern Polytechnical University, China
TU2.MM-9.9: CLASSIFICATION OF MULTI-RESOLUTION HYPERSPECTRAL DATA BY CONVOLUTIONAL NEURAL NETWORKS
Takato Yamada, Akira Iwasaki, University of Tokyo, Japan
TU2.MM-9.10: A COMPARATIVE STUDY OF NOISE SENSITIVITY ON DIFFERENT HYPERSPECTRAL CLASSIFICATION METHODS
Congyu Li, Xinxin Liu, Xudong Kang, Shutao Li, Hunan University, China

Quicklinks

Downloads

Programme guide