paper-with-me

Papers

Domain Discrepancy Measure for Complex Models in Unsupervised Domain Adaptation

2019-01-30 · Jongyeong Lee, Nontawat Charoenphakdee, Seiichi Kuroki, Masashi Sugiyama

Appropriately evaluating the discrepancy between domains is essential for the success of unsupervised domain adaptation. In this paper, we first point out that existing discrepancy measures are less informative when complex models such as deep neural networks are used, in addition to the facts that they can be computationally highly demanding and their range of applications is limited only to binary classification. We then propose a novel domain discrepancy measure, called the paired hypotheses discrepancy (PHD), to overcome these shortcomings. PHD is computationally efficient and applicable to multi-class classification. Through generalization error bound analysis, we theoretically show that PHD is effective even for complex models. Finally, we demonstrate the practical usefulness of PHD through experiments.

📄 PDF Abstract BibTeX arXiv:1901.10654

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationClassificationDomain AdaptationGeneral ClassificationMulti-class ClassificationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Implicit Task-Driven Probability Discrepancy Measure for Unsupervised Domain Adaptation

2021-12-01 · NeurIPS 2021 12 · Mao Li, Kaiqi Jiang, Xinhua Zhang

Probability discrepancy measure is a fundamental construct for numerous machine learning models such as weakly supervised learning and generative modeling. However, most measures overlook the fact that the distributions…

Domain AdaptationUnsupervised Domain AdaptationWeakly-supervised Learning

Unsupervised Domain Adaptation Based on Source-guided Discrepancy

2018-09-11 · Seiichi Kuroki, Nontawat Charoenphakdee, Han Bao, Junya Honda 외

Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsuper…

Domain AdaptationUnsupervised Domain Adaptation

Stein Discrepancy for Unsupervised Domain Adaptation

2025-02-05 · Anneke von Seeger, Dongmian Zou, Gilad Lerman

Unsupervised domain adaptation (UDA) leverages information from a labeled source dataset to improve accuracy on a related but unlabeled target dataset. A common approach to UDA is aligning representations from the source…

Domain AdaptationUnsupervised Domain Adaptation

Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

2019-04-18 · CVPR 2019 6 · Junbao Zhuo, Shuhui Wang, Shuhao Cui, Qingming Huang

We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T i…

ClassificationGeneral Classification

Learning Smooth Representation for Unsupervised Domain Adaptation

2019-05-26 · Guanyu Cai, Lianghua He, Mengchu Zhou, Hesham Alhumade 외

Typical adversarial-training-based unsupervised domain adaptation methods are vulnerable when the source and target datasets are highly-complex or exhibit a large discrepancy between their data distributions. Recently, s…

Domain AdaptationUnsupervised Domain Adaptation