会议论文

Jin, Qiwen

英文

2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021)

2021

1885-1889

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

JUN 06-11, 2021

ELECTR NETWORK

[Jin, Qiwen;Ma, Yong;Mei, Xiaoguang;Ma, Jiayi] Wuhan Univ, Elect Informat Sch, Wuhan 430072, Peoples R China.^[Ma, Yong;Mei, Xiaoguang;Ma, Jiayi] Wuhan Univ, Inst Aerosp Sci & Technol, Wuhan 430072, Peoples R China.^[Li, Hao] Wuhan Polytech Univ, Coll Math & Comp Sci, Wuhan 430023, Peoples R China.

IEEE, Inst Elect & Elect Engineers, Signal Proc Soc

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

978-1-7281-7605-5

10.1109/ICASSP39728.2021.9414810

National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61903279]

本校为其他机构

Recently, the learning-based method has received much attention in the unsupervised hyperspectral unmixing, yet their ability to extract physically meaningful endmembers remains limited and the performance has not been satisfactory. In this paper, we propose a novel two-stream Dirichlet-net, termed as uTDN, to address the above problems. The weight-sharing architecture makes it possible to transfer the intrinsic properties of the endmembers during the process of unmixing, which can help to correct the network converging towards a more accurate and interpretable unmixing solution. Besides, the ...