paper-with-me

홈 › Papers

Hierarchical Bayesian Framework for Multisource Domain Adaptation

2025-12-21 · Alexander M. Glandon, Khan M. Iftekharuddin arxiv

Multisource domain adaptation (MDA) aims to use multiple source datasets with available labels to infer labels on a target dataset without available labels for target supervision. Prior works on MDA in the literature is ad-hoc as the pretraining of source models is either based on weight sharing or uses independently trained models. This work proposes a Bayesian framework for pretraining in MDA by considering that the distributions of different source domains are typically similar. The Hierarchical Bayesian Framework uses similarity between the different source data distributions to optimize the pretraining for MDA. Experiments using the proposed Bayesian framework for MDA show that our framework improves accuracy on recognition tasks for a large benchmark dataset. Performance comparison with state-of-the-art MDA methods on the challenging problem of human action recognition in multi-domain benchmark Daily-DA RGB video shows the proposed Bayesian Framework offers a 17.29% improvement in accuracy when compared to the state-of-the-art methods in the literature.

📄 PDF Abstract BibTeX arXiv:2512.18553

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionDomain Adaptation

Similar Papers 제목 키워드 기반

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers

2015-03-24 · Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant

In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distributio…

Domain Adaptation

Population-aware Hierarchical Bayesian Domain Adaptation

2018-11-21 · Vishwali Mhasawade, Nabeel Abdur Rehman, Rumi Chunara

Population attributes are essential in health for understanding who the data represents and precision medicine efforts. Even within disease infection labels, patients can exhibit significant variability; "fever" may mean…

Domain Adaptation

Multiple Source Domain Adaptation with Adversarial Learning

2018-01-01 · ICLR 2018 1 · Han Zhao, Shanghang Zhang, Guanhang Wu, Jo\~{a}o P. Costeira 외

While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple …

Domain AdaptationSentiment Analysis

Multiple Source Domain Adaptation with Adversarial Training of Neural Networks

2017-05-26 · Han Zhao, Shanghang Zhang, Guanhang Wu, João P. Costeira 외

While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple …

Domain AdaptationSentiment Analysis

Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019

2019-10-08 · Yingwei Pan, Yehao Li, Qi Cai, Yang Chen 외

This notebook paper presents an overview and comparative analysis of our systems designed for the following two tasks in Visual Domain Adaptation Challenge (VisDA-2019): multi-source domain adaptation and semi-supervised…

Domain AdaptationSelf-LearningSemi-supervised Domain Adaptation