Open AccessRegularised transfer learning for hyperspectral image classification
Author(s) -
Shi Qian,
Zhang Yipeng,
Liu Xiaoping,
Zhao Kefei
Publication year - 2019
Publication title -
iet computer vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.38
H-Index - 37
eISSN - 1751-9640
pISSN - 1751-9632
DOI - 10.1049/iet-cvi.2018.5145
Subject(s) - hyperspectral imaging , subspace topology , pattern recognition (psychology) , artificial intelligence , divergence (linguistics) , feature (linguistics) , computer science , transfer of learning , domain (mathematical analysis) , image (mathematics) , feature learning , bregman divergence , sampling (signal processing) , representation (politics) , mathematics , computer vision , statistics , political science , law , mathematical analysis , philosophy , linguistics , filter (signal processing) , politics
This study presents a transfer learning method for addressing the insufficient sample problem in hyperspectral image classification. In order to find common feature representation for both the source domain and target domain, we introduce a regularisation based on Bregman divergence into the objective function of the subspace learning algorithm, which can minimise the Bregman divergence between the distribution of training samples in the source domain and the test samples in the target domain. Hyperspectral image with biased sampling is used to evaluate the effectiveness of the proposed method. The results show that the proposed method can achieve a higher classification accuracy than traditional subspace learning methods under the condition of biased sampling.