Filters








272,659 Hits in 3.7 sec

Optimal Transport for Domain Adaptation [article]

Nicolas Courty, Devis Tuia
2016 arXiv   pre-print
In this paper, we propose a regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains.  ...  Among the many strategies proposed to adapt a domain to another, finding a common representation has shown excellent properties: by finding a common representation for both domains, a single classifier  ...  REGULARIZED DISCRETE OPTIMAL TRANSPORT This section discusses the problem of optimal transport for domain adaptation.  ... 
arXiv:1507.00504v2 fatcat:belapr6k5jfsjb5dqbs22xo6de

Optimal Transport for Domain Adaptation

Nicolas Courty, Remi Flamary, Devis Tuia, Alain Rakotomamonjy
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we propose a regularized unsupervised optimal transportation model to perform the alignment of the representations in the source and target domains.  ...  Domain adaptation is one of the most challenging tasks of modern data analytics.  ...  REGULARIZED DISCRETE OPTIMAL TRANSPORT This section discusses the problem of optimal transport for domain adaptation.  ... 
doi:10.1109/tpami.2016.2615921 pmid:27723579 fatcat:ednzn6li7jekra6yyybpoiiyo4

CytOpT: Optimal Transport with Domain Adaptation for Interpreting Flow Cytometry data [article]

Paul Freulon, Jérémie Bigot, Boris P. Hejblum
2022 arXiv   pre-print
We introduce a new algorithm, referred to as CytOpT, using regularized optimal transport to directly estimate the different cell population proportions from a biological sample characterized with flow  ...  Due to the high-dimensionality of flow cytometry data, we use stochastic algorithms to approximate the regularized Wasserstein metric to solve the optimization problem involved in the estimation of optimal  ...  The author would also like to thank Kalidou Ba for developing the CytOpT packages.  ... 
arXiv:2006.09003v5 fatcat:4olivyjimres3bobuoyto4zpy4

Joint Distribution Optimal Transportation for Domain Adaptation [article]

Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy
2017 arXiv   pre-print
We propose a solution of this problem with optimal transport, that allows to recover an estimated target P^f_t=(X,f(X)) by optimizing simultaneously the optimal coupling and f.  ...  This paper deals with the unsupervised domain adaptation problem, where one wants to estimate a prediction function f in a given target domain without any labeled sample by exploiting the knowledge available  ...  The authors also wish to thank Kai Zhang and Qiaojun Wang for providing the Wifi localization dataset.  ... 
arXiv:1705.08848v2 fatcat:osto5inknrbxhbinsazx35xg6y

Deep Optimal Transport for Domain Adaptation on SPD Manifolds [article]

Ce Ju, Cuntai Guan
2022 arXiv   pre-print
In addition, we propose a computational scheme under the optimal transport framework, Deep Optimal Transport (DOT), for general computation, using the generalized joint distribution adaptation approach  ...  We then formalize this problem from an optimal transport perspective and derive an optimal transport framework on SPD manifolds for supervised learning.  ...  Corollary 3.1 asserts DOT is an optimal transport to adapt the marginal and conditional distributions from the source and target domains on SPD manifolds by parallelly transporting the source and target  ... 
arXiv:2201.05745v2 fatcat:aww3jhll7zbmrk4zynfvhhh4o4

Optimal Transport for Multi-source Domain Adaptation under Target Shift [article]

Ievgen Redko, Nicolas Courty, Rémi Flamary, Devis Tuia
2019 arXiv   pre-print
To address this issue, we design a method based on optimal transport, a theory that has been successfully used to tackle adaptation problems in machine learning.  ...  In this paper, we propose to tackle the problem of reducing discrepancies between multiple domains referred to as multi-source domain adaptation and consider it under the target shift assumption: in all  ...  In this paper, we propose a new algorithm for correcting the target shift based on optimal transport (OT).  ... 
arXiv:1803.04899v3 fatcat:ftfsfwctzjcb5ef6yxysohdgta

Functional optimal transport: map estimation and domain adaptation for functional data [article]

Jiacheng Zhu, Aritra Guha, Dat Do, Mengdi Xu, XuanLong Nguyen, Ding Zhao
2022 arXiv   pre-print
Optimal transport for functional data analysis provides a useful framework of treatment for such domains.  ...  We introduce a formulation of optimal transport problem for distributions on function spaces, where the stochastic map between functional domains can be partially represented in terms of an (infinite-dimensional  ...  Optimal transport domain adaptation: We applied our proposed method on an optimal transport based domain adaptation problem (OTDA) for motion prediction.  ... 
arXiv:2102.03895v4 fatcat:jw4lbetkl5cy3mmofmusoz5cvu

Domain Adaptation with Optimal Transport on the Manifold of SPD matrices [article]

Or Yair, Felix Dietrich, Ronen Talmon, Ioannis G. Kevrekidis
2020 arXiv   pre-print
In this paper, we address the problem of Domain Adaptation (DA) using Optimal Transport (OT) on Riemannian manifolds.  ...  We model the difference between two domains by a diffeomorphism and use the polar factorization theorem to claim that OT is indeed optimal for DA in a well-defined sense, up to a volume preserving map.  ...  In general, under this setting, there are three natural alternatives for applying OT and obtaining the transport plan for domain adaptation.  ... 
arXiv:1906.00616v4 fatcat:lr3p3u76qjdnnf2c2fnzvehfqq

DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation [article]

Bharath Bhushan Damodaran, Benjamin Kellenberger, Rémi Flamary, Devis Tuia, Nicolas Courty
2018 arXiv   pre-print
In this work we explore a solution, named DeepJDOT, to tackle this problem: through a measure of discrepancy on joint deep representations/labels based on optimal transport, we not only learn new data  ...  We applied DeepJDOT to a series of visual recognition tasks, where it compares favorably against state-of-the-art deep domain adaptation methods.  ...  We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
arXiv:1803.10081v3 fatcat:ukza6mmg2zdztivi4falukk7uy

Hierarchical Optimal Transport for Unsupervised Domain Adaptation [article]

Mourad El Hamri and Younès Bennani and Issam Falih and Hamid Ahaggach
2021 arXiv   pre-print
In this paper, we propose a novel approach for unsupervised domain adaptation, that relates notions of optimal transport, learning probability measures and unsupervised learning.  ...  The proposed approach, HOT-DA, is based on a hierarchical formulation of optimal transport, that leverages beyond the geometrical information captured by the ground metric, richer structural information  ...  Since then, several optimal transport based domain adaptation methods have emerged.  ... 
arXiv:2112.02073v1 fatcat:yn7mek3xwzhstka6bubcvpwmu4

Connecting adversarial attacks and optimal transport for domain adaptation [article]

Arip Asadulaev, Vitaly Shutov, Alexander Korotin, Alexander Panfilov, Andrey Filchenkov
2022 arXiv   pre-print
We present a novel algorithm for domain adaptation using optimal transport. In domain adaptation, the goal is to adapt a classifier trained on the source domain samples to the target domain.  ...  We conduct experiments on Digits and Modern Office-31 datasets and achieve improvement in performance for simple discrete optimal transport solvers for all adaptation tasks.  ...  This work was supported by the Analytical Center for the Government of the Russian Federation (IGK 000000D730321P5Q0002), agreement No. 70-2021-00141.  ... 
arXiv:2205.15424v2 fatcat:btvlfsqhl5ayzd3jdtklqdxi7u

Metric Learning-enhanced Optimal Transport for Biochemical Regression Domain Adaptation [article]

Fang Wu, Nicolas Courty, Zhang Qiang, jiyu Cui, Ziqing Li
2022 arXiv   pre-print
To meet this challenge, researchers have used optimal transport (OT) to perform representation alignment between the source and target domains.  ...  Generalizing knowledge beyond source domains is a crucial prerequisite for many biomedical applications such as drug design and molecular property prediction.  ...  Optimal Transport for Regressions Unsupervised Domain Adaptation UDA is common in biochemistry.  ... 
arXiv:2202.06208v2 fatcat:yodnvw4ldbg3boknp77io5ttpa

Feature Selection for Unsupervised Domain Adaptation using Optimal Transport [article]

Léo Gautheron, Ievgen Redko, Carole Lartizien
2018 arXiv   pre-print
In this paper, we propose a new feature selection method for unsupervised domain adaptation based on the emerging optimal transportation theory.  ...  We build upon a recent theoretical analysis of optimal transport in domain adaptation and show that it can directly suggest a feature selection procedure leveraging the shift between the domains.  ...  Optimal transport and domain adaptation The use of optimal transport for domain adaptation has been studied for the first time in [5] .  ... 
arXiv:1806.10861v1 fatcat:tly5tbob2nfttghfvobhhdycre

Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation

Renjun Xu, Pelen Liu, Liyan Wang, Chao Chen, Jindong Wang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we present Reliable Weighted Optimal Transport (RWOT) for unsupervised domain adaptation, including novel Shrinking Subspace Reliability (SSR) and weighted optimal transport strategy.  ...  Among them, the optimal transport is a promising metric to align the representations of the source and target domains.  ...  Weighted Optimal Transport Optimal transport for domain adaptation performs the alignment of the sample representations in the source and target domains.  ... 
doi:10.1109/cvpr42600.2020.00445 dblp:conf/cvpr/XuLWC020 fatcat:n2o2frrmrbaplouusdhnrzwlee

Metric Learning in Optimal Transport for Domain Adaptation

Tanguy Kerdoncuff, Rémi Emonet, Marc Sebban
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In this paper, we propose to use Optimal Transport (OT) and its associated Wassertein distance to perform this alignment.  ...  This prompts us to optimize the ground metric of OT to reduce the target risk; (ii) from this theoretical analysis, we design an algorithm (MLOT) which optimizes a Mahalanobis distance leading to a transportation  ...  For example, [Azimi and Fern, 2009] proposed an adaptive clustering ensemble selection method; applied internal validity indices to select based clustering results.  ... 
doi:10.24963/ijcai.2020/295 dblp:conf/ijcai/0006DL20 fatcat:cnyi6n55h5ekpbr24rzsudlm6i
« Previous Showing results 1 — 15 out of 272,659 results