paper-with-me

Papers

Sample-to-Sample Correspondence for Unsupervised Domain Adaptation

2018-05-01 · Debasmit Das, C. S. George Lee

The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and testing (target) domains is known as domain adaptation. We propose an unsupervised version of domain adaptation that considers the presence of only unlabelled data in the target domain. Our approach centers on finding correspondences between samples of each domain. The correspondences are obtained by treating the source and target samples as graphs and using a convex criterion to match them. The criteria used are first-order and second-order similarities between the graphs as well as a class-based regularization. We have also developed a computationally efficient routine for the convex optimization, thus allowing the proposed method to be used widely. To verify the effectiveness of the proposed method, computer simulations were conducted on synthetic, image classification and sentiment classification datasets. Results validated that the proposed local sample-to-sample matching method out-performs traditional moment-matching methods and is competitive with respect to current local domain-adaptation methods.

📄 PDF Abstract BibTeX arXiv:1805.00355

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationGeneral Classificationimage-classificationImage ClassificationSentiment AnalysisSentiment ClassificationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Transferable Feature Learning on Graphs Across Visual Domains

2021-01-01 · Ronghang Zhu, Xiaodong Jiang, Jiasen Lu, Sheng Li

Unsupervised domain adaptation has attracted increasing attention in recent years, which adapts classifiers to an unlabeled target domain by exploiting a labeled source domain. To reduce discrepancy between source and ta…

Domain AdaptationUnsupervised Domain Adaptation

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

2021-10-13 · NeurIPS 2021 12 · Yin Zhao, Minquan Wang, Longjun Cai

Eliminating the covariate shift cross domains is one of the common methods to deal with the issue of domain shift in visual unsupervised domain adaptation. However, current alignment methods, especially the prototype bas…

Domain AdaptationUnsupervised Domain Adaptation

Towards Unsupervised Domain Adaptation via Domain-Transformer

2022-02-24 · Ren Chuan-Xian, Zhai Yi-Ming, Luo You-Wei, Yan Hong

As a vital problem in pattern analysis and machine intelligence, Unsupervised Domain Adaptation (UDA) attempts to transfer an effective feature learner from a labeled source domain to an unlabeled target domain. Inspired…

Domain AdaptationGeneralization BoundsLearning TheoryTransfer Learning+1

Unsupervised Deep Domain Adaptation for Pedestrian Detection

2018-02-09 · Lihang Liu, Weiyao Lin, Lisheng Wu, Yong Yu 외

This paper addresses the problem of unsupervised domain adaptation on the task of pedestrian detection in crowded scenes. First, we utilize an iterative algorithm to iteratively select and auto-annotate positive pedestri…

Domain AdaptationPedestrian DetectionUnsupervised Domain Adaptation

Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment

2023-08-24 · François Painblanc, Laetitia Chapel, Nicolas Courty, Chloé Friguet 외

While large volumes of unlabeled data are usually available, associated labels are often scarce. The unsupervised domain adaptation problem aims at exploiting labels from a source domain to classify data from a related, …

Domain AdaptationDynamic Time WarpingTime SeriesUnsupervised Domain Adaptation