FAST OPTIMAL TRANSPORT FOR LATENT DOMAIN ADAPTATION

被引：0

作者：

Roheda, Siddharth ^{[1
]}

Panahi, Ashkan ^{[2
]}

Krim, Hamid ^{[3
]}

机构：

[1] Samsung Res Inst Bangalore, Bangalore, India

[2] Chalmers Univ, Dept Comp Sci & Engn, Gothenburg, Sweden

[3] North Carolina State Univ, Elect & Comp Engn Dept, Raleigh, NC USA

来源：

2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP | 2023年

关键词：

Optimal Transport; Domain Adaptation;

D O I：

10.1109/ICIP49359.2023.10222535

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we address the problem of unsupervised Domain Adaptation. The need for such an adaptation arises when the distribution of the target data differs from that which is used to develop the model and the ground truth information of the target data is unknown. We propose an algorithm that uses optimal transport theory with a verifiably efficient and implementable solution to learn the best latent feature representation. This is achieved by minimizing the cost of transporting the samples from the target domain to the distribution of the source domain.

引用

页码：1810 / 1814

页数：5

共 50 条

[1] Optimal Transport for Domain Adaptation
Courty, Nicolas
Flamary, Remi
Tuia, Devis
Rakotomamonjy, Alain
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (09) : 1853 - 1865
[2] Theoretical Analysis of Domain Adaptation with Optimal Transport
Redko, Ievgen
Habrard, Amaury
Sebban, Marc
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2017, PT II, 2017, 10535 : 737 - 753
[3] Optimal Transport with Dimensionality Reduction for Domain Adaptation
Li, Ping
Ni, Zhiwei
Zhu, Xuhui
Song, Juan
Wu, Wenying
SYMMETRY-BASEL, 2020, 12 (12): : 1 - 18
[4] Hierarchical optimal transport for unsupervised domain adaptation
Mourad El Hamri
Younès Bennani
Issam Falih
Machine Learning, 2022, 111 : 4159 - 4182
[5] Hierarchical optimal transport for unsupervised domain adaptation
El Hamri, Mourad
Bennani, Younes
Falih, Issam
MACHINE LEARNING, 2022, 111 (11) : 4159 - 4182
[6] A MINIMALIST APPROACH FOR DOMAIN ADAPTATION WITH OPTIMAL TRANSPORT
Asadulaev, Arip
Shutov, Vitaly
Korotin, Alexander
Panfilov, Alexander
Kontsevaya, Vladislava
Filchenkov, Andrey
CONFERENCE ON LIFELONG LEARNING AGENTS, VOL 232, 2023, 232 : 1009 - 1024
[7] Metric Learning in Optimal Transport for Domain Adaptation
Kerdoncuff, Tanguy
Emonet, Remi
Sebban, Marc
PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 2162 - 2168
[8] Domain Adaptation as Optimal Transport on Grassmann Manifolds
Long, Tianhang
Sun, Yanfeng
Gao, Junbin
Hu, Yongli
Yin, Baocai
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (10) : 7196 - 7209
[9] Differentially Private Optimal Transport: Application to Domain Adaptation
LeTien, Nam
Habrard, Amaury
Sebban, Marc
PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2852 - 2858
[10] Open Set Domain Adaptation Using Optimal Transport
Kechaou, Marwa
Herault, Romain
Alaya, Mokhtar Z.
Gasso, Gilles
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2020, PT I, 2021, 12457 : 412 - 435

← 1 2 3 4 5 →