Artigos Científicos



Heterogeneous Domain Adaptation Network Based on Autoencoder

Baixar (pdf, 64 KB)


Heterogeneous Domain Adaptation Network Based on Autoencoder
Xuesong Wang, Yuting Ma, Yuhu Cheng, Liang Zou & Joel. J. P. C. Rodrigues

Heterogeneous domain adaptation is a more challenging problem than homogeneous domain adaptation. The
transfer effect is not ideal caused by shallow structure which cannot adequately describe the probability distribution and
obtain more effective features. In this paper, we propose a heterogeneous domain adaptation network based on autoencoder,
in which two sets of autoencoder networks are used to project the source-domain and target-domain data to a shared feature
space to obtain more abstractive feature representations. In the last feature and classification layer, the marginal and
conditional distributions can be matched by empirical maximum mean discrepancy metric to reduce distribution difference.
To preserve the consistency of geometric structure and label information, a manifold alignment term based on labels is
introduced. The classification performance can be improved further by making full use of label information of both domains.
The experimental results of 16 cross-domain transfer tasks verify that HDANA outperforms several state-of-the-art

heterogeneous domain adaptation; autoencoder; maximum mean discrepancy; manifold alignment

@ Entre em contato

Instituto Nacional de Telecomunicações – Inatel

Campus em Santa Rita do Sapucaí - MG - Brasil

Av. João de Camargo, 510 - Centro - 37540-000

+55 (35) 3471 9200

Escritório em São Paulo - SP - Brasil

WTC Tower, 18º andar - Conjunto 1811/1812

Av. das Nações Unidas, 12.551 - Brooklin Novo - 04578-903

+55 (11) 3043 6015 |