Filters








165,376 Hits in 5.0 sec

Open Set Domain Adaptation using Optimal Transport [article]

Marwa Kechaou, Romain Hérault, Mokhtar Z. Alaya, Gilles Gasso
2020 arXiv   pre-print
The first step of the approach aims at rejecting the samples issued from these new classes using an optimal transport plan.  ...  The second step solves the target (class ratio) shift still as an optimal transport problem.  ...  In this paper, we address the open set DA using optimal transport.  ... 
arXiv:2010.01045v1 fatcat:c4arqaxavngdrgqhhvcwngkz7q

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  
strategy in open set domain adaptation.  ...  Figure 1 :Figure 2 : 12 The necessity of the proposed method partial optimal transport for open set domain adaptation. Three colors denote three sets of data.  ... 
doi:10.24963/ijcai.2020/352 dblp:conf/ijcai/XuLZC0LYY20 fatcat:lc7elmrxzbe5bc2624mwbnsq2m

Multitemporal classification without new labels: A solution with optimal transport

Devis Tuia, Remi Flamary, Alain Rakotomamonjy, Nicolas Courty
2015 2015 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images (Multi-Temp)  
We study optimal transport as a way to match the image-specific distributions and propose two regularization schemes, one supervised and one semi-supervised, to obtain more robust and semantic matchings  ...  In this paper we propose a relative normalization technique to perform domain adaptation, i.e. to make the data distribution in the images more similar before classification.  ...  OPTIMAL TRANSPORT FOR DOMAIN ADAPTATION Consider two data sources (domains): first is a source domain, X s , that is labeled.  ... 
doi:10.1109/multi-temp.2015.7245773 dblp:conf/multitemp/TuiaFRC15 fatcat:ih2uafedfzb4tm7hh6fa2hcniu

The Building Blocks of Information Are Selections – Let's Define Them Globally! [chapter]

Wolfgang Orthuber
2021 Studies in Health Technology and Informatics  
We can globalize this by using an efficient global pointer (UL) as "context". The article explains new globally identified and defined "Domain Vectors" (DVs) for transporting digital information.  ...  This opens up far-reaching new possibilities for the efficient exchange, comparison and search of information.  ...  In medical reports, DVs with such adapted domains can be used to reduce non-reproducible parts step by step.  ... 
doi:10.3233/shti210576 pmid:34734854 fatcat:vsk5tpygxzh6pg5ihmax44vf3m

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.  ...  In our method, we use optimal transport to map target samples to the domain named source fiction. This domain differs from the source but is accurately classified by the source domain classifier.  ...  The optimal transport results in domain adaptation depend on the cost function c ( 2).  ... 
arXiv:2205.15424v1 fatcat:rq5ad6dtsjffbbw5vyx4hyecc4

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  
Heterogeneous domain adaptation (HDA) aims to exploit knowledge from a heterogeneous source domain to improve the learning performance in a target domain.  ...  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.  ...  2017B090901008, 2017A010101011, 2017B090910005, and Fundamental Research Funds for the Central Universities D2172500, D2172480, and Pearl River S&T Nova Program of Guangzhou 201806010081 and CCF-Tencent Open  ... 
doi:10.24963/ijcai.2018/412 dblp:conf/ijcai/Yan0WMTW18 fatcat:4iejfpaqmrbbdduidxzmcqpj34

Adaptive area-preserving parameterization of open and closed anatomical surfaces [article]

Gary P. T. Choi, Amita Giri, Lalan Kumar
2021 arXiv   pre-print
We further develop a set of spherical harmonics-like basis functions defined over the adaptive spherical cap domain, which we call the adaptive harmonics.  ...  More broadly, the idea of using an adaptive parameter domain allows easy handling of a wide range of biomedical shapes.  ...  Optimal Mass Transport and Area-Preserving Map The theory of optimal mass transport (OMT) has been studied for over two centuries [40] , [41] , and recently it has been shown to be closely related to  ... 
arXiv:2111.04265v1 fatcat:cnrtctmyu5ay7ihufnx3lfe3le

Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation [article]

Aparna Balagopalan, Jekaterina Novikova, Matthew B. A. McDermott, Bret Nestor, Tristan Naumann, Marzyeh Ghassemi
2019 arXiv   pre-print
We utilize out-of-domain, unpaired, single-speaker, healthy speech data for training multiple Optimal Transport (OT) domain adaptation systems.  ...  We learn mappings from other languages to English and detect aphasia from linguistic characteristics of speech, and show that OT domain adaptation improves aphasia detection over unilingual baselines for  ...  We use Optimal Transport, an embedding-based method of domain adaptation (Sec. 4.1).  ... 
arXiv:1912.04370v1 fatcat:iid33agodrbhtccjmvsqgr2xdm

Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation [article]

Chen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, Daniel Ulbricht
2019 arXiv   pre-print
In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric  ...  Future work includes extension of our approach to domain randomization [68] , open set adaptation [59] , and zero-shot domain adaptation [49] .  ...  Method We first introduce unsupervised domain adaptation setting in Section 3.1. Second, we briefly review the concept of optimal transport in Section 3.2.  ... 
arXiv:1903.04064v1 fatcat:emwkvazl5rarnbhfl2f2m24g5q

Semi-supervised Optimal Transport with Self-paced Ensemble for Cross-hospital Sepsis Early Detection [article]

Ruiqing Ding, Yu Zhou, Jie Xu, Yan Xie, Qiqiang Liang, He Ren, Yixuan Wang, Yanlin Chen, Leye Wang, Man Huang
2021 arXiv   pre-print
the semi-supervised domain adaptation based on optimal transport theory with self-paced under-sampling to avoid a negative transfer possibly caused by covariate shift and class imbalance.  ...  Different from the supervised learning setting, we need to use known information (e.g., from another hospital with rich labeled data) to help build a model with acceptable performance, i.e., transfer learning  ...  More specifically, in semi-supervised domain adaptation with optimal transport, we devise a label adaptive optimal transport strategy to achieve the precise-pairwise optimal transport and an intra-domain  ... 
arXiv:2106.10352v1 fatcat:wwmoxns35jbdzpqaq77rgoh6qe

A Moving Mesh Adaptation Method by Optimal Transport

Dongsheng An, Na Lei, Tong Zhao, Hang Si, Xianfeng Gu
2021 Zenodo  
In this paper, we propose a moving mesh method to generate adaptive meshes by optimal transport.  ...  Given an initial mesh and a scalar density function defined on the mesh domain, our method will redistribute the mesh nodes such that they are adapted to the density function.  ...  Therefore, we can use Newton's method to optimize the energy. Fig. 1 shows an optimal transportation map computed using this method.  ... 
doi:10.5281/zenodo.5559175 fatcat:vfc2d2qplbdlfbar7tvljlrpqi

Optimal Transport with Dimensionality Reduction for Domain Adaptation

Ping Li, Zhiwei Ni, Xuhui Zhu, Juan Song, Wenying Wu
2020 Symmetry  
Domain adaptation manages to learn a robust classifier for target domain, using the source domain, but they often follow different distributions.  ...  To bridge distribution shift between the two domains, most of previous works aim to align their feature distributions through feature transformation, of which optimal transport for domain adaptation has  ...  Optimal Transport for Domain Adaptation Optimal transport (OT) can learn the optimal transport plan (OTP) according to Wasserstein distance, thus the source instances can be transported to the target domain  ... 
doi:10.3390/sym12121994 fatcat:25hwkwcfsradhgnuobpbjpqj2e

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  ...  A particular case is found in the use of optimal transport, introduced for domain adaptation by [13, 14] .  ... 
arXiv:1705.08848v2 fatcat:osto5inknrbxhbinsazx35xg6y

A Prototype-Oriented Framework for Unsupervised Domain Adaptation [article]

Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng, Shujian Zhang, Hao Zhang, Bo Chen, Mingyuan Zhou
2021 arXiv   pre-print
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.  ...  We demonstrate the general applicability of our method on a wide range of scenarios, including single-source, multi-source, class-imbalance, and source-private domain adaptation.  ...  In each variant, we solve for the optimal couplings using the optimal transport formulation.  ... 
arXiv:2110.12024v1 fatcat:axhkrc3xijdstg3l7lwsezsy7e

Control Plane Architectures Enabling Transport Network Adaptive and Autonomic Operation

Ramon Casellas, Ricard Vilalta, Arturo Mayoral, Ricardo Martínez, Raül Muñoz, Luis M. Contreras
2017 Zenodo  
In this line, the steady increase in the use of open and standard interfaces and data modelling languages, as well as the wide adoption (in a vendor independent way) of model-driven solutions and a unified  ...  cases such as in-operation network planning, on-demand network optimization and parameter tuning.  ...  of Open Source projects and open and standard interfaces.  ... 
doi:10.5281/zenodo.833149 fatcat:ou7zioeilfdstnf6b56ogoaw74
« Previous Showing results 1 — 15 out of 165,376 results