基于张量表示的域适配的迁移学习中特征表示方法

doi:10.3969/j.issn.0372-2112.2020.02.019

电子学报 ›› 2020, Vol. 48 ›› Issue (2): 359-368.DOI: 10.3969/j.issn.0372-2112.2020.02.019

基于张量表示的域适配的迁移学习中特征表示方法

赵鹏, 王美玉, 纪霞, 刘慧婷

1. 安徽大学计算机智能与信号处理教育部重点实验室, 安徽合肥 230601;
2. 安徽大学计算机科学与技术学院, 安徽合肥 230601

收稿日期:2019-05-22 修回日期:2019-09-12 出版日期:2020-02-25
- 作者简介:
- 赵鹏女,1976年生于安徽合肥.博士,副教授,硕士生导师,CCF会员,主要研究方向为机器学习、图像理解.E-mail:zhaopeng_ad@163.com;王美玉 女,1994年生于安徽黄山.硕士研究生,主要研究方向为迁移学习、图像标注;纪霞女,1983年生于安徽宣城.博士,讲师,硕士生导师,CCF会员,主要研究方向为智能信息处理;刘慧婷 女,1978年生于安徽阜阳.博士,副教授,硕士生导师,主要研究方向为机器学习、智能推荐.
- 基金资助:
- 国家自然科学基金 (No.61602004）; 安徽省高校自然科学研究重点项目 (No.KJ2018A0013，No.KJ2017A011）; 安徽省自然科学基金 (No.1908085MF188，No.1908085MF182）; 安徽省重点研究与开发计划项目 (No.1804d08020309）

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

ZHAO Peng, WANG Mei-yu, JI Xia, LIU Hui-ting

1. Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, Anhui 230601;
2. School of Computer Science and Technology, Anhui University, Hefei, Anhui 230601, China

Received:2019-05-22 Revised:2019-09-12 Online:2020-02-25 Published:2020-02-25

摘要/Abstract

摘要： 本文提出一种新的基于张量表示的域适配迁移学习中的特征表示方法，即融合联合域对齐和适配正则化的基于张量表示的迁移学习特征表示方法.当源域和目标域差异很大时，仅将源域对齐潜在共享空间，会造成数据扭曲过大.为缓解此问题，本文方法提出联合域对齐，即源域和目标域同时对齐共享子空间.并且本文方法将适配正则化引入张量表示空间求解.本文适配正则化包括动态分布对齐和图适配，以缩小域间分布差异和保留样本间流行一致性.最后融合联合域对齐，动态分布对齐和图适配，通过联合优化求解获得共享子空间表示.几个公共的跨域数据集上的大量实验结果表明了本文方法优于其它主流的迁移学习方法，验证了本文方法的有效性.

关键词: 张量表示, 迁移学习, 域适配

Abstract: 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.

Key words: tensor representation, transfer learning, domain adaption

中图分类号:

TP391.41

赵鹏, 王美玉, 纪霞, 刘慧婷. 基于张量表示的域适配的迁移学习中特征表示方法[J]. 电子学报, 2020, 48(2): 359-368.

ZHAO Peng, WANG Mei-yu, JI Xia, LIU Hui-ting. A Novel Feature Representation Based on Tensor and Domain Adaption for Transfer Learning[J]. Acta Electronica Sinica, 2020, 48(2): 359-368.

参考文献

[1] Pan S J,Tsang I W,Kwok J T,et al.Domain adaptation via transfer component analysis[J].IEEE Transactions on Neural Networks,2011,22(2):199-210.
[2] Pan S J,Kwok J T,Yang Q.Transfer learning via dimensionality reduction[A].Association for the Advance of Artificial Intelligence[C].Menlo Park,CA:AAAI,2008.677-682.
[3] Long M,Wang J,Ding G,et al.Transfer feature learning with joint distribution adaptation[A].IEEE International Conference on Computer Vision[C].Washington:IEEE,2013.2200-2207.
[4] Wang J,Chen Y,Hao S,et al.Balanced distribution adaptation for transfer learning[A].IEEE International Conference on Data Mining[C].Washington: IEEE,2017.1129-1134.
[5] Zhang L,Liu Y,He Z,et al.Anti-drift in E-nose:A subspace projection approach with drift reduction[J].Sensors and Actuators B:Chemical,2017,253:407-417.
[6] Blitzer J,McDonald R,Pereira F.Domain adaptation with structural correspondence learning[A].2006 Conference on Empirical Methods in Natural Language Processing[C].Sydney:Association for Computational Linguistics,2006.120-128.
[7] Satpal S,Sarawagi S.Domain adaptation of conditional probability models via feature subsetting[A].European Conference on Principles of Data Mining and Knowledge Discovery[C].Berlin Heidelberg:Springer-Verlag,2007.224-235.
[8] Fernando B,Habrard A,Sebban M,et al.Unsupervised visual domain adaptation using subspace alignment[A].IEEE Conference on Computer Vision[C].Washington:IEEE,2013.2960-2967.
[9] Ghifary M,Balduzzi D,Kleijn W B,et al.Scatter component analysis:A unified framework for domain adaptation and domain generalization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(7):1414-1430.
[10] Ben X,Gong C,Zhang P,et al.Coupled bilinear discriminant projection for cross-view gait recognition[J].IEEE Transactions on Circuits and Systems for Video Technology,2019,(99):1-1.
[11] Shashua A,Levin A.Linear image coding for regression and classification using the tensor-Rank principle[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington:IEEE,2001.42-49.
[12] Ben X,Zhang P,Lai Z,et al.A general tensor representation framework for cross-view gait recognition[J].Pattern Recognition,2019,90:87-98.
[13] Kolda T,Bader B.The TOPHITS model for higher-order web link analysis[A].Workshop on Link Analysis,Counterterrorism and Security[C].Bethesda:Link Analysis,Counterterrorism and Security,2006.7:26-29.
[14] Lu H,Zhang L,Cao Z,et al.When unsupervised domain adaptation meets tensor representations[A].IEEE International Conference on Computer Vision[C].Washington:IEEE,2017.599-608.
[15] Wang J,Feng W,Chen Y,et al.Visual domain adaptation with manifold embedded distribution alignment[A].ACM Multimedia Conference on Multimedia Conference[C].New York:ACM,2018.402-410.
[16] Gong B,Shi Y,Sha F,et al.Geodesic flow kernel for unsupervised domain adaptation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington:IEEE,2012.2066-2073.
[17] Venkateswara H,Eusebio J,Chakraborty S,et al.Deep hashing network for unsupervised domain adaptation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington:IEEE,2017.5018-5027.
[18] Arbelaez P,Maire M,Fowlkes C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011.33(5):898-916.
[19] Sun B,Feng J,Saenko K.Return of frustratingly easy domain adaptation[A].Thirtieth AAAI Conference on Artificial Intelligence[C].Phoenix,Arizona:AAAI,2016.2058-2065.
[20] Zhang J,Li W,Ogunbona P.Joint geometrical and statistical alignment for visual domain adaptation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Washington:IEEE,2017.1859-1867.

基于张量表示的域适配的迁移学习中特征表示方法

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

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	邵志文, 周勇, 谭鑫, 马利庄, 刘兵, 姚睿. 基于深度学习的表情动作单元识别综述[J]. 电子学报, 2022, 50(8): 2003-2017.
[2]	李维刚, 甘平, 谢璐, 李松涛. 基于样本对元学习的小样本图像分类方法[J]. 电子学报, 2022, 50(2): 295-304.
[3]	陈文俊, 杨春玲. 图像压缩感知的特征域优化及自注意力增强神经网络重构算法[J]. 电子学报, 2022, 50(11): 2629-2637.
[4]	张小恒, 张馨月, 李勇明, 王品, 刘玉川. 面向帕金森病语音诊断的非监督两步式卷积稀疏迁移学习算法[J]. 电子学报, 2022, 50(1): 177-184.
[5]	李勇斌, 王彬, 邵高平, 邵帅. 一种基于RCGAN的水声通信信号降噪方法[J]. 电子学报, 2022, 50(1): 54-62.
[6]	唐焕玲, 郑涵, 刘艳红, 马思源, 窦全胜, 鲁明羽. Tr-SLDA:一种面向交叉领域的迁移主题模型[J]. 电子学报, 2021, 49(3): 605-613.
[7]	张锦, 李阳, 任传伦, 黄炼, 王帅辉, 段晔鑫, 潘志松, 谢钧. 基于帧间高级特征差分的跨场景视频前景分割算法[J]. 电子学报, 2021, 49(10): 2032-2040.
[8]	王格格, 郭涛, 余游, 苏菡. 基于生成对抗网络的无监督域适应分类模型[J]. 电子学报, 2020, 48(6): 1190-1197.
[9]	张红斌, 蒋子良, 熊其鹏, 武晋鹏, 邬任重, 袁天, 姬东鸿. 基于改进的有效区域基因选择与跨模态语义挖掘的图像属性标注[J]. 电子学报, 2020, 48(4): 790-799.
[10]	权宇, 李志欣, 张灿龙, 马慧芳. 融合深度扩张网络和轻量化网络的目标检测模型[J]. 电子学报, 2020, 48(2): 390-397.
[11]	刘真, 田靖玉, 苑宝鑫, 孙永奇. 基于知识聚合和迁移的跨领域推荐算法[J]. 电子学报, 2020, 48(10): 1928-1932.
[12]	季鼎承, 蒋亦樟, 王士同. 基于域与样例平衡的多源迁移学习方法[J]. 电子学报, 2019, 47(3): 692-699.
[13]	余游, 冯林, 王格格, 徐其凤. 一种基于伪标签的半监督少样本学习模型[J]. 电子学报, 2019, 47(11): 2284-2291.
[14]	任卓君, 陈光, 卢文科. 基于N-gram特征的恶意代码可视化方法[J]. 电子学报, 2019, 47(10): 2108-2115.
[15]	胡根生, 查慧敏, 梁栋, 鲍文霞. 结合分类与迁移学习的薄云覆盖遥感图像地物信息恢复[J]. 电子学报, 2017, 45(12): 2855-2862.