Filters








62,785 Hits in 3.8 sec

Joint Distribution Optimal Transportation for Domain Adaptation [article]

Nicolas Courty, Rémi Flamary, Amaury Habrard, Alain Rakotomamonjy
2017 arXiv   pre-print
Our work makes the following assumption: there exists a non-linear transformation between the joint feature/label space distributions of the two domain P_s and P_t.  ...  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.  ...  The authors also wish to thank Kai Zhang and Qiaojun Wang for providing the Wifi localization dataset.  ... 
arXiv:1705.08848v2 fatcat:osto5inknrbxhbinsazx35xg6y

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

Joint distribution optimal transportation for domain adaptation [article]

Rémi Flamary
2017
Our work makes the following assumption: there exists a non-linear transformation between the joint feature/labels space distributions of the two domain ${\mathrm{ps}}$ and ${\mathrm{pt}}$.  ...  We propose a solution of this problem with optimal transport, that allows to recover an estimated target ${\mathrm{pt}}^f=(X,f(X))$ by optimizing simultaneously the optimal coupling and $f$.  ...  The authors also wish to thank Kai Zhang and Qiaojun Wang for providing the Wifi localization dataset.  ... 
doi:10.14288/1.0357417 fatcat:xiso2adwpbb6lnuaye3rulrtku

Partial Coupling of Optimal Transport for Spoken Language Identification [article]

Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai
2022 arXiv   pre-print
distribution alignment (JDA) model based on optimal transport (OT).  ...  Fully matching training and test domains for distribution alignment may introduce negative domain transfer.  ...  In order to measure the distribution discrepancy, optimal transport provides a powerful tool for measuring the distance between two distributions, i.e., optimal transport distance. on this JDA-POT adaptation  ... 
arXiv:2203.17036v1 fatcat:djkzm7z76rgzfag5rg4dvhl2yq

Searching for Optimal Subword Tokenization in Cross-domain NER [article]

Ruotian Ma, Yiding Tan, Xin Zhou, Xuanting Chen, Di Liang, Sirui Wang, Wei Wu, Tao Gui, Qi Zhang
2022 arXiv   pre-print
Specifically, we re-tokenize the input words of the source domain to approach the target subword distribution, which is formulated and solved as an optimal transport problem.  ...  Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).  ...  Acknowledgements The authors wish to thank the anonymous reviewers for their helpful comments.  ... 
arXiv:2206.03352v1 fatcat:hntpwkifvrf47djnpnh2dwon2m

Label Distribution for Learning with Noisy Labels

Yun-Peng Liu, Ning Xu, Yu Zhang, Xin Geng
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
Thus, designing algorithms that deal with noisy labels is of great importance for learning robust DNNs.  ...  To address the problem, this paper proposes a novel method named Label Distribution based Confidence Estimation (LDCE).  ...  Acknowledgements Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2020/352 dblp:conf/ijcai/XuLZC0LYY20 fatcat:lc7elmrxzbe5bc2624mwbnsq2m

Bures Joint Distribution Alignment with Dynamic Margin for Unsupervised Domain Adaptation [article]

Yong-Hui Liu, Chuan-Xian Ren, Xiao-Lin Xu, Ke-Kun Huang
2022 arXiv   pre-print
To address this problem, we propose the Bures Joint Distribution Alignment (BJDA) algorithm which directly models the joint distribution shift based on the optimal transport theory in the infinite-dimensional  ...  However, the joint dependency among the feature and the label is crucial for the adaptation task and is not fully exploited.  ...  [10] investigate an optimal transport transformation to align the joint distributions between differ-ent domains and propose joint distribution optimal transport (JDOT). Damodaran et al.  ... 
arXiv:2203.06836v1 fatcat:55z2fizqsveexcc6ids5ze7iem

Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation

Yuguang Yan, Wen Li, Hanrui Wu, Huaqing Min, Mingkui Tan, Qingyao Wu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
In this paper, we propose a novel semi-supervised algorithm for HDA by exploiting the theory of optimal transport (OT), a powerful tool originally designed for aligning two different distributions.  ...  Heterogeneous domain adaptation (HDA) aims to exploit knowledge from a heterogeneous source domain to improve the learning performance in a target domain.  ...  Acknowledgments This work was supported by National Natural Science Foundation of China (NSFC) 61502177 and 61602185, and Recruitment Program for Young Professionals, and Guangdong Provincial Scientific  ... 
doi:10.24963/ijcai.2018/412 dblp:conf/ijcai/Yan0WMTW18 fatcat:4iejfpaqmrbbdduidxzmcqpj34

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.  ...  This way, we exploit at the same time the labeled samples in the source and the distributions observed in both domains.  ...  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

Distance Metric Facilitated Transportation between Heterogeneous Domains

Han-Jia Ye, Xiang-Rong Sheng, De-Chuan Zhan, Peng He
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
reduced with learned optimal transportation.  ...  Note that both source domain and cross-domain relationship are fully utilized in MapHere, which helps improve target classification task a lot.  ...  We compare with optimal transport for domain adaptation with two different class regularizers OT IT and OT GL [Courty et al., 2017b] , mapping estimation for optimal transport OT MT [Perrot et al., 2016  ... 
doi:10.24963/ijcai.2018/418 dblp:conf/ijcai/YeSZH18 fatcat:ajokrlayerf35ct2mixtmo23le

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.  ...  ) probability distributions.  ...  JOINT CLASS PROPORTION AND OPTIMAL TRANSPORT (JCPOT) In this section, we introduce the proposed JCPOT method, that aims at finding the optimal transportation plan and estimating class proportions jointly  ... 
arXiv:1803.04899v3 fatcat:ftfsfwctzjcb5ef6yxysohdgta

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.  ...  [22] designs a conditional alignment network based on adversarial learning. (6) Deep Joint Distribution Optimal Transport (DeepJDOT) [7] adapts optimal transport strategy in deep domain adaptation  ... 
doi:10.1109/cvpr42600.2020.00445 dblp:conf/cvpr/XuLWC020 fatcat:n2o2frrmrbaplouusdhnrzwlee

Multi-Scale Capsule Attention Network and Joint Distributed Optimal Transport for Bearing Fault Diagnosis under Different Working Loads

Zihao Sun, Xianfeng Yuan, Xu Fu, Fengyu Zhou, Chengjin Zhang
2021 Sensors  
Using the domain adaptation ability of joint distribution optimal transport, the feature distribution of fault data under different loads is aligned, and domain-invariant features are learned.  ...  optimal transport (MSCAN-JDOT) is proposed for bearing fault diagnosis under different loads.  ...  Acknowledgments: We would like to convey our deep appreciation to the editors and the reviewers for their insightful comments and constructive suggestions, which were very helpful in the improvement of  ... 
doi:10.3390/s21196696 pmid:34641016 fatcat:zz3abnpefjbahbunlamyi7tcu4

On Scalable and Efficient Computation of Large Scale Optimal Transport [article]

Yujia Xie, Minshuo Chen, Haoming Jiang, Tuo Zhao, Hongyuan Zha
2019 arXiv   pre-print
SPOT also allows us to efficiently sample from the optimal transport plan, which benefits downstream applications such as domain adaptation.  ...  Specifically, we approximate the optimal transport plan by a pushforward of a reference distribution, and cast the optimal transport problem into a minimax problem.  ...  Bharath Bhushan Damodaran for his timely help about the implementation of DeepJDOT method.  ... 
arXiv:1905.00158v3 fatcat:bwmv6lxxpveqbbnxqri7l5q5vq
« Previous Showing results 1 — 15 out of 62,785 results