paper-with-me

Papers

Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learning

2024-07-29 · Eduardo Fernandes Montesuma, Stevan Le Stanc, Fred Ngolè Mboula

This paper addresses the challenge of online multi-source domain adaptation (MSDA) in transfer learning, a scenario where one needs to adapt multiple, heterogeneous source domains towards a target domain that comes in a stream. We introduce a novel approach for the online fit of a Gaussian Mixture Model (GMM), based on the Wasserstein geometry of Gaussian measures. We build upon this method and recent developments in dataset dictionary learning for proposing a novel strategy in online MSDA. Experiments on the challenging Tennessee Eastman Process benchmark demonstrate that our approach is able to adapt \emph{on the fly} to the stream of target domain data. Furthermore, our online GMM serves as a memory, representing the whole stream of data.

📄 PDF Abstract BibTeX arXiv:2407.19853

Code (0)

등록된 구현이 없습니다.

Tasks

Dictionary LearningDomain AdaptationTransfer Learning

Similar Papers 제목 키워드 기반

Model Selection with Nonlinear Embedding for Unsupervised Domain Adaptation

2017-06-23 · Hemanth Venkateswara, Shayok Chakraborty, Troy McDaniel, Sethuraman Panchanathan

Domain adaptation deals with adapting classifiers trained on data from a source distribution, to work effectively on data from a target distribution. In this paper, we introduce the Nonlinear Embedding Transform (NET) fo…

Domain AdaptationGeneral ClassificationModel SelectionUnsupervised Domain Adaptation

Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation

2020-04-09 · ECCV 2020 8 · Da Li, Timothy Hospedales

Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have…

Domain AdaptationMeta-LearningMMEMulti-Source Unsupervised Domain Adaptation+2

Casting a BAIT for Offline and Online Source-free Domain Adaptation

2020-10-23 · Shiqi Yang, Yaxing Wang, Joost Van de Weijer, Luis Herranz 외

We address the source-free domain adaptation (SFDA) problem, where only the source model is available during adaptation to the target domain. We consider two settings: the offline setting where all target data can be vis…

Domain AdaptationSource-Free Domain AdaptationUnsupervised Domain Adaptation

Towards Better Stability and Adaptability: Improve Online Self-Training for Model Adaptation in Semantic Segmentation

2023-01-01 · CVPR 2023 1 · Dong Zhao, Shuang Wang, Qi Zang, Dou Quan 외

Unsupervised domain adaptation (UDA) in semantic segmentation transfers the knowledge of the source domain to the target one to improve the adaptability of the segmentation model in the target domain. The need to acc…

Domain AdaptationSemantic SegmentationSource-Free Domain AdaptationUnsupervised Domain Adaptation

Automatic Online Multi-Source Domain Adaptation

2021-09-05 · Renchunzi Xie, Mahardhika Pratama

Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and never-ending environments of data strea…

DenoisingDomain AdaptationOnline Domain AdaptationTransfer Learning