A Novel Feature Representation Based on Tensor and Domain Adaption for Transfer Learning

被引：0

作者：

Zhao P. ^{[1
,2
]}

Wang M.-Y. ^{[1
,2
]}

Ji X. ^{[1
,2
]}

Liu H.-T. ^{[1
,2
]}

机构：

[1] Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, 230601, Anhui

[2] School of Computer Science and Technology, Anhui University, Hefei, 230601, Anhui

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2020年 / 48卷 / 02期

关键词：

Domain adaption; Tensor representation; Transfer learning;

D O I：

10.3969/j.issn.0372-2112.2020.02.019

中图分类号：

学科分类号：

摘要：

A novel feature representation based on tensor and domain adaption for transfer learning is proposed, which combines joint domain alignment and adaptation regularization. When the difference between the source domain and the target domain is very large, only aligning the source domain to the potential shared subspace will result in too much data distortion. To alleviate this problem, this paper proposes joint domain alignment, which aligns the source domain and the target domain to the potential shared subspaces simultaneously. Furthermore, the adaption regularization is introduced into the subspace learning based on tensor. In the proposed method, adaptation regularization includes dynamic distribution alignment and graph adaptation to reduce the distribution differences among different domains and preserve the manifold consistency. Finally, the joint domain alignment, dynamic distributed alignment and graph adaptation are fused, and the joint optimization is utilized to obtain the feature representation. Extensive experiments on several common cross-domain datasets show that the proposed method outperforms the state-of-the-art on the tasks of transfer learning and the effectiveness of the proposed method is verified. © 2020, Chinese Institute of Electronics. All right reserved.

引用

页码：359 / 368

页数：9

共 20 条

[1] Pan S.J., Tsang I.W., Kwok J.T., Et al., Domain adaptation via transfer component analysis, IEEE Transactions on Neural Networks, 22, 2, pp. 199-210, (2011)
[2] Pan S.J., Kwok J.T., Yang Q., Transfer learning via dimensionality reduction, Association for the Advance of Artificial Intelligence, pp. 677-682, (2008)
[3] Long M., Wang J., Ding G., Et al., Transfer feature learning with joint distribution adaptation, IEEE International Conference on Computer Vision, pp. 2200-2207, (2013)
[4] Wang J., Chen Y., Hao S., Et al., Balanced distribution adaptation for transfer learning, IEEE International Conference on Data Mining, pp. 1129-1134, (2017)
[5] Zhang L., Liu Y., He Z., Et al., Anti-drift in E-nose: A subspace projection approach with drift reduction, Sensors and Actuators B: Chemical, 253, pp. 407-417, (2017)
[6] Blitzer J., McDonald R., Pereira F., Domain adaptation with structural correspondence learning, 2006 Conference on Empirical Methods in Natural Language Processing, pp. 120-128, (2006)
[7] Satpal S., Sarawagi S., Domain adaptation of conditional probability models via feature subsetting, European Conference on Principles of Data Mining and Knowledge Discovery, pp. 224-235, (2007)
[8] Fernando B., Habrard A., Sebban M., Et al., Unsupervised visual domain adaptation using subspace alignment, IEEE Conference on Computer Vision, pp. 2960-2967, (2013)
[9] Ghifary M., Balduzzi D., Kleijn W.B., Et al., Scatter component analysis: A unified framework for domain adaptation and domain generalization, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 7, pp. 1414-1430, (2017)
[10] Ben X., Gong C., Zhang P., Et al., Coupled bilinear discriminant projection for cross-view gait recognition, IEEE Transactions on Circuits and Systems for Video Technology, 99, (2019)

← 1 2 →