基于联合层级粒包络判别特征学习的无监督领域自适应方法
Unsupervised Domain Adaptation Based on Joint Hierarchical Granularity Envelope Discriminative Feature Learning
- 电子学报 2025年 页码：1-13
- 作者机构：
重庆大学微电子与通信工程学院，重庆 400000
- 作者简介：
[ "李普飞 男，1995年12月出生于河北省邯郸市.重庆大学微电子与通信工程学院博士研究生.主要研究方向为机器学习、迁移学习. E-mail: lipufei@cqu.edu.cn" ]
[ "王品 （通讯作者） 女，1979年11月出生于江苏省盐城市.现为重庆大学微电子与通信工程学院副教授，硕士生导师.主要研究领域为图像处理与识别." ]
[ "李勇明 男，1976年9月出生于四川省绵阳市.现为重庆大学微电子与通信工程学院教授，博士生导师.主要研究方向为医学信号处理、机器学习.E-mail: yongmingli@cqu.edu.cn" ]
[ "张锦华 男，1999年1月出生于山东省济宁市.重庆大学微电子与通信工程学院硕士研究生.主要研究方向为深度学习与图像处理.E-mail: 202312021035@cqu.edu.cn" ]
[ "颜芳 女，1979年10月出生于甘肃省天水市.重庆大学微电子与通信工程学院副教授.主要研究领域为智能信息处理.E-mail: yanfang@cqu.edu.cn" ]
- 基金信息：国家自然科学基金(U21A20448;61771080)
DOI：10.12263/DZXB.20240793
中图分类号： TP391.4;收稿：2024-08-28，
修回：2024-11-11，
网络出版：2025-03-04，
- 稿件说明：
移动端阅览
李普飞, 王品, 李勇明, 等. 基于联合层级粒包络判别特征学习的无监督领域自适应方法[J/OL]. 电子学报, 2025,1-13.
LI Pu-fei, WANG Pin, LI Yong-ming, et al. Unsupervised Domain Adaptation Based on Joint Hierarchical Granularity Envelope Discriminative Feature Learning[J/OL]. ACTA ELECTRONICA SINICA, 2025, 1-13.
李普飞, 王品, 李勇明, 等. 基于联合层级粒包络判别特征学习的无监督领域自适应方法[J/OL]. 电子学报, 2025,1-13. DOI： 10.12263/DZXB.20240793.
LI Pu-fei, WANG Pin, LI Yong-ming, et al. Unsupervised Domain Adaptation Based on Joint Hierarchical Granularity Envelope Discriminative Feature Learning[J/OL]. ACTA ELECTRONICA SINICA, 2025, 1-13. DOI： 10.12263/DZXB.20240793.
摘要
无监督领域自适应（Unsupervised Domain Adaptation，UDA）是模式识别中的重要研究领域，旨在将标注完善但分布不同的源域知识转移到未标注的目标域数据上.现有方法仅关注源域和目标域原始样本分布的对齐，因此在分布差异较大时效果不佳.近年来，基于语义的UDA方法引入了类别信息.然而，类别信息过于粗略，难以充分反映源域和目标域的分布.为了解决这一问题，本文提出了一种用于无监督领域自适应的联合层级粒包络判别特征学习方法，该方法在三个层次上聚合了原始样本对、类别和粒包络信息，从而由粗到细地反映了数据分布.具体来说，本文引入了“知识金字塔”理论，通过构造粒包络，连接原始样本与类中心，建立三层粒度样本，替代现有方法中单层粒度的原始样本.同时，基于本文方法设计了一种迭代式聚类算法，揭示了样本间的关联信息，在原始样本与类中心之间生成粒包络.通过使用Bagging集成模式整合这三种粒度层，并对不同层次的粒度进行加权，以确保令人满意的精度.在基准数据集上的实验结果表明，本文方法能有效减小域间差异并提升分类精度，且优于其它主流领域自适应方法.
Abstract
Unsupervised domain adaptation(UDA) is a significant research area that aims to transfer knowledge from source data
which is well-labeled but distributed differently
to unlabeled target data. Existing methods only considered aligning the distributions of the original source and target domain samples
suffering from the big difference in the distributions. In recent years
semantic-based UDA has integrated category information on this basis. However
the category information is too coarse and cannot fully reflect the distributions of source and target domain. To solve this problem
a joint hierarchical granularity envelope(JHGE) discriminative feature learning approach is proposed
which integrates information from original sample pairs
categories
and granular envelopes at three levels. This method can reflect the distribution from coarse to fine. Specifically
the "knowledge pyramid" theory is firstly incorporated into the UDA framework to realize multi-sample granularity-based semantic representation. Besides
granular envelopes are created to connect the original samples with class centers
establishing three layers of sample granularity
which replace the single layer of original samples in existing UDA methods. Secondly
an iterative clustering approach is developed to uncover associative information between samples
generating granular envelopes between original samples and class centers. This three-layer sample granularity enriches the informative content of the existing UDA methods. Thirdly
a bagging ensemble mode is implemented to integrate the three-layer granularity spaces. The different layers of granularity are weighted to ensure satisfactory accuracy. Experimental results on benchmark datasets demonstrate that this method can effectively reduce differences across domain and outperforms the state-of-the-art domain adaptation methods.
关键词
Keywords
references
王格格 , 郭涛 , 余游 , 等 . 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 .
WANG G G , GUO T , YU Y , et al . Unsupervised domain adaptation classification model based on generative adversarial network [J ] . Acta Electronica Sinica , 2020 , 48 ( 6 ): 1190 - 1197 . (in Chinese)
赵鹏 , 王美玉 , 纪霞 , 等 . 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 P , WANG M Y , JI X , et al . A novel feature representation based on tensor and domain adaption for transfer learning [J ] . Acta Electronica Sinica , 2020 , 48 ( 2 ): 359 - 368 . (in Chinese)
蒋晓玲 , 吴映波 , 陈蒙 , 等 . 基于跨域结构保持投影的异构在线多源迁移学习方法 [J ] . 电子学报 , 2023 , 51 ( 8 ): 1983 - 1994 .
JIANG X L , WU Y B , CHEN M , et al . Heterogeneous online multi-source transfer learning with cross-domain structure preserving projection [J ] . Acta Electronica Sinica , 2023 , 51 ( 8 ): 1983 - 1994 . (in Chinese)
ZHANG L , GAO X . Transfer adaptation learning: A decade survey [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 1 ): 23 - 44 .
LONG M , WANG J , DING G , et al . Transfer feature learning with joint distribution adaptation [C ] // 2013 IEEE International Conference on Computer Vision . Piscataway : IEEE , 2013 : 2200 - 2207 .
SAITO K , WATANABE K , USHIKU Y , et al . Maximum classifier discrepancy for unsupervised domain adaptation [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3723 - 3732 .
LI S , LIU C H , SU L , et al . Discriminative transfer feature and label consistency for cross-domain image classification [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 11 ): 4842 - 4856 .
GONG B , SHI Y , SHA F , et al . Geodesic flow kernel for unsupervised domain adaptation [C ] // 2012 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2012 : 2066 - 2073 .
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 .
SUN B , SAENKO K . Deep CORAL: Correlation alignment for deep domain adaptation [C ] // Computer Vision - ECCV 2016 Workshops . Cham : Springer , 2016 : 443 - 450 .
TZENG E , HOFFMAN J , SAENKO K , et al . Adversarial discriminative domain adaptation [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 2962 - 2971 .
WANG W , SHEN Z , LI D , et al . Probability-based graph embedding cross-domain and class discriminative feature learning for domain adaptation [J ] . IEEE Transactions on Image Processing , 2023 , 32 : 72 - 87 .
JING M , ZHAO J , LI J , et al . Adaptive component embedding for domain adaptation [J ] . IEEE Transactions on Cybernetics , 2021 , 51 ( 7 ): 3390 - 3403 .
LU Y , LI D , WANG W , et al . Discriminative invariant alignment for unsupervised domain adaptation [J ] . IEEE Transactions on Multimedia , 2022 , 24 : 1871 - 1882 .
YANG L , ZHOU Q , LU B . Marginal subspace learning with group low-rank for unsupervised domain adaptation [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 7 ): 9122 - 9135 .
CHENG D , LI Y , XIA S , et al . A fast granular-ball-based density peaks clustering algorithm for large-scale data [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2023 , 35 ( 12 ): 1 - 14 .
XIA S , WANG C , WANG G , et al . GBRS: A unified granular-ball learning model of pawlak rough set and neighborhood rough set [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 36 ( 1 ): 1 - 15 .
GRETTON A , BORGWARDT K , RASCH M , et al . A kernel method for the two-sample-problem [C ] // Proceedings of the 20th International Conference on Neural Information Processing Systems . Cambridge : MIT Press , 2006 : 513 - 520 .
TZENG E , HOFFMAN J , ZHANG N , et al . Deep domain confusion: Maximizing for domain invariance [EB/OL ] . ( 2014-12-10 )[ 2025-01-06 ] . http://arxiv.org/abs/1412.3474 http://arxiv.org/abs/1412.3474 .
LONG M , CAO Y , WANG J , et al . Learning transferable features with deep adaptation networks [C ] // Proceedings of the 32nd International Conference on Machine Learning . Lille : PMLR , 2015 : 97 - 105 .
SUN B , FENG J , SAENKO K . Return of frustratingly easy domain adaptation [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Washington : AAAI Press , 2016 : 2508 - 2605 .
GANIN Y , LEMPITSKY V . Unsupervised domain adaptation by backpropagation [C ] // Proceedings of the 32nd International Conference on Machine Learning . Lille : PMLR , 2015 : 1180 - 1189 .
LONG M , ZHU H , WANG J , et al . Deep transfer learning with joint adaptation networks [C ] // International Conference on Machine Learning . Sydney : JMLR , 2017 : 2208 - 2217 .
ZHANG J , LI W , OGUNBONA P . Joint geometrical and statistical alignment for visual domain adaptation [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 5150 - 5158 .
WANG J , CHEN Y , HAO S , et al . Balanced distribution adaptation for transfer learning [C ] // 2017 IEEE International Conference on Data Mining (ICDM) . Piscataway : IEEE , 2017 : 1129 - 1134 .
WANG J , FENG W , CHEN Y , et al . Visual domain adaptation with manifold embedded distribution alignment [C ] // ACM International Conference on Multimedia . New York : ACM , 2018 : 402 - 410 .
LI S , SONG S , HUANG G , et al . Domain invariant and class discriminative feature learning for visual domain adaptation [J ] . IEEE Transactions on Image Processing , 2018 , 27 ( 9 ): 4260 - 4273 .
LIANG J , HE R , SUN Z , et al . Aggregating randomized clustering-promoting invariant projections for domain adaptation [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2019 , 41 ( 5 ): 1027 - 1042 .
PEI Z , CAO Z , LONG M , et al . Multi-adversarial domain adaptation [C ] // Proceedings of the AAAI Conference on Artificial Intelligence . Washington : AAAI Press . 2018 : 3934 - 3941 .
LONG M , CAO Z , WANG J , et al . Conditional adversarial domain adaptation [C ] // Proceedings of the 32nd International Conference on Neural Information Processing Systems . Cambridge : MIT Press , 2018 : 1647 - 1657 .
DENG Z , LUO Y , ZHU J . Cluster alignment with a teacher for unsupervised domain adaptation [C ] // International Conference on Computer Vision . Piscataway : IEEE , 2019 : 9943 - 9952 .
YU C , WANG J , CHEN Y , et al . Transfer learning with dynamic adversarial adaptation network [C ] // International Conference on Data Mining . Piscataway : IEEE , 2019 : 778 - 786 .
CHEN W , HU H . Generative attention adversarial classification network for unsupervised domain adaptation [J ] . Pattern Recognition , 2020 , 107 : 107440 .
YANG B , YUEN P C . Learning adaptive geometry for unsupervised domain adaptation [J ] . Pattern Recognition , 2021 , 110 : 107638 .
HUANG J , XIAO N , ZHANG L . Balancing transferability and discriminability for unsupervised domain adaptation [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2024 , 35 ( 4 ): 5807 - 5814 .
SIM T , BAKER S , BSAT M . The CMU pose, illumination, and expression database [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2003 , 25 ( 12 ): 1615 - 1618 .
HUTCHISON D , KANADE T , KITTLER J , et al . Adapting Visual Category Models to New Domains [M ] // Computer Vision – ECCV 2010 . Berlin : Springe , 2010 : 213 - 226 .
DONAHUE J , JIA Y , VINYALS O , et al . DeCAF: A deep convolutional activation feature for generic visual recognition [C ] // Proceedings of the 31st International Conference on Machine Learning . New York : ICML , 2013 : 647 - 655 .
HE K , ZHANG X , REN S , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 : 770 - 778 .
FUKUNAGA K , NARENDRA P M . A branch and bound algorithm for computing k-nearest neighbors [J ] . IEEE Transactions on Computers , 1975 , 24 ( 7 ): 750 - 753 .
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . Imagenet classification with deep convolutional neural networks [C ] // Proceedings of the 26nd International Conference on Neural Information Processing Systems . Cambridge, MA, USA : MIT Press , 2012 : 1106 - 1114 .
ZHUO J B , WANG S H , ZHANG W G , et al . Deep unsupervised convolutional domain adaptation [C ] // Proceedings of the 25th ACM International Conference on Multimedia . New York : ACM , 2017 : 261 - 269 .
ZHUO J B , WANG S H , ZHANG W G , et al . Deep unsupervised convolutional domain adaptation [C ] // Proceedings of the 25th ACM International Conference on Multimedia . New York : ACM , 2017 : 261 - 269 . [LinkOut ]
0
浏览量
4
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 京ICP备09064830号-19
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies