Active multi-kernel domain adaptation for hyperspectral image classification

PATTERN RECOGNITION

卷:77

Article

Deng, Cheng¹  Liu, Xianglong²  Li, Chao¹  Tao, Dacheng³ 

[1] Xidian Univ, Sch Elect Engn, Xian 710071, Shaanxi, Peoples R China

[2] Beihang Univ, State Key Lab Software Dev Environm, Beijing 100191, Peoples R China

[3] Univ Sydney, FEIT, Sch IT, UBTECH Sydney AI Ctr, Sydney, NSW, Australia

关键词: Active learning;    Multi-kernel;    Domain adaptation;    Hyperspectral image classification;    Remote sensing;   

DOI  :  10.1016/j.patcog.2017.10.007

来源: Elsevier

【 摘 要 】

Recent years have witnessed the quick progress of the hyperspectral images (HSI) classification. Most of existing studies either heavily rely on the expensive label information using the supervised learning or can hardly exploit the discriminative information borrowed from related domains. To address this issues, in this paper we show a novel framework addressing HSI classification based on the domain adaptation (DA) with active learning (AL). The main idea of our method is to retrain the multi-kernel classifier by utilizing the available labeled samples from source domain, and adding minimum number of the most informative samples with active queries in the target domain. The proposed method adaptively combines multiple kernels, forming a DA classifier that minimizes the bias between the source and target domains. Further equipped with the nested actively updating process, it sequentially expands the training set and gradually converges to a satisfying level of classification performance. We study this active adaptation framework with the Margin Sampling (MS) strategy in the HSI classification task. Our experimental results on two popular HSI datasets demonstrate its effectiveness. (C) 2017 Elsevier Ltd. All rights reserved.

【 授权许可】

Free