Domain Adaption Algorithm Based on ELM Autoencoder
DENG Wanyu
QU Yutao
ZHANG Qian
Abstract：ELM Autoencoder(ELM-AE)can extract data features,a new domain adaption algorithm is designed based on ELM-AE,which describe the subspaces of source and target domain by ELM-AE,and then subspace alignment is carryed out to project different domains into a common new space.The widely experimental results on Office[1]/Caltech256[2]data sets show that the proposed algorithm can achieve better classification accuracy than other state-of-art transfer learning algorithms in most cases.
Keywords：ELM-AEsubspacesubspace alignmentdomain adaption
Publication Date：2018-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 857-860 )