TY - JOUR
T1 - Discriminative Manifold Distribution Alignment for Domain Adaptation
AU - Yao, Siya
AU - Kang, Qi
AU - Zhou, Mengchu
AU - Rawa, Muhyaddin J.
AU - Albeshri, Aiiad
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 51775385 and Grant 61703279; in part by the Strategy Research Project of Artificial Intelligence Algorithms of Ministry of Education of China; in part by the Shanghai Industrial Collaborative Science and Technology Innovation Project under Grant 2021-cyxt2-kj10; in part by the Shanghai Municipal Science and Technology Major Project under Grant 2021SHZDZX0100; in part by the Fundamental Research Funds for the Central Universities; and in part by the Ministry of Education and King Abdulaziz University, Jeddah, Saudi Arabia, through Institutional Fund Projects under Grant IFPNC-001- 135-2020.
Publisher Copyright:
© 2022 IEEE.
PY - 2023/2/1
Y1 - 2023/2/1
N2 - Domain adaptation (DA) aims to accomplish tasks on unlabeled target data by learning and transferring knowledge from related source domains. In order to learn a discriminative and domain-invariant model, a critical step is to align source and target data well and thus reduce their distribution divergence. But existing DA methods mainly align the global feature distributions in distorted original space, which neglects their fine-grained local information and intrinsic geometrical structures. Moreover, some methods rely heavily on pseudo-labels to align features, which may undermine adaptation performance and lead to negative transfer. We propose an efficient discriminative manifold distribution alignment (DMDA) approach, which improves feature transferability by aligning both global and local distributions and refines a discriminative model by learning geometrical structures in manifold space. In addition, when learning geometrical structures, DMDA is exempt from the uncertainty and error brought by pseudo-labels of a target domain. It is very concise and efficient to be implemented by integrating learning steps and obtaining solutions directly. Extensive experiments on 68 DA tasks from seven benchmarks and subsequent analyses show that DMDA outperforms the compared methods in both classification accuracy and time efficiency, thus representing a significant advance in the DA field.
AB - Domain adaptation (DA) aims to accomplish tasks on unlabeled target data by learning and transferring knowledge from related source domains. In order to learn a discriminative and domain-invariant model, a critical step is to align source and target data well and thus reduce their distribution divergence. But existing DA methods mainly align the global feature distributions in distorted original space, which neglects their fine-grained local information and intrinsic geometrical structures. Moreover, some methods rely heavily on pseudo-labels to align features, which may undermine adaptation performance and lead to negative transfer. We propose an efficient discriminative manifold distribution alignment (DMDA) approach, which improves feature transferability by aligning both global and local distributions and refines a discriminative model by learning geometrical structures in manifold space. In addition, when learning geometrical structures, DMDA is exempt from the uncertainty and error brought by pseudo-labels of a target domain. It is very concise and efficient to be implemented by integrating learning steps and obtaining solutions directly. Extensive experiments on 68 DA tasks from seven benchmarks and subsequent analyses show that DMDA outperforms the compared methods in both classification accuracy and time efficiency, thus representing a significant advance in the DA field.
KW - Distribution alignment
KW - domain adaptation (DA)
KW - image classification
KW - manifold learning
KW - transfer learning (TL)
UR - http://www.scopus.com/inward/record.url?scp=85136850192&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85136850192&partnerID=8YFLogxK
U2 - 10.1109/TSMC.2022.3195239
DO - 10.1109/TSMC.2022.3195239
M3 - Article
AN - SCOPUS:85136850192
SN - 2168-2216
VL - 53
SP - 1183
EP - 1197
JO - IEEE Transactions on Systems, Man, and Cybernetics: Systems
JF - IEEE Transactions on Systems, Man, and Cybernetics: Systems
IS - 2
M1 - 9863704
ER -