paper-with-me

Papers

Unsupervised Domain Adaptation using Graph Transduction Games

2019-05-06 · Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich, Twan van Laarhoven, Elena Marchiori, Marcello Pelillo

Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain. In this paper, we propose to cast this problem in a game-theoretic setting as a non-cooperative game and introduce a fully automatized iterative algorithm for UDA based on graph transduction games (GTG). The main advantages of this approach are its principled foundation, guaranteed termination of the iterative algorithms to a Nash equilibrium (which corresponds to a consistent labeling condition) and soft labels quantifying the uncertainty of the label assignment process. We also investigate the beneficial effect of using pseudo-labels from linear classifiers to initialize the iterative process. The performance of the resulting methods is assessed on publicly available object recognition benchmark datasets involving both shallow and deep features. Results of experiments demonstrate the suitability of the proposed game-theoretic approach for solving UDA tasks.

📄 PDF Abstract BibTeX arXiv:1905.02036

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationObject RecognitionUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Ancient Coin Classification Using Graph Transduction Games

2018-10-02 · Sinem Aslan, Sebastiano Vascon, Marcello Pelillo

Recognizing the type of an ancient coin requires theoretical expertise and years of experience in the field of numismatics. Our goal in this work is automatizing this time consuming and demanding task by a visual classif…

ClassificationGeneral Classificationimage-classificationImage Classification

Deep Transfer Network: Unsupervised Domain Adaptation

2015-03-02 · Xu Zhang, Felix Xinnan Yu, Shih-Fu Chang, Shengjin Wang

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the d…

Domain AdaptationUnsupervised Domain Adaptation

GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation

2019-06-01 · CVPR 2019 6 · Xinhong Ma, Tianzhu Zhang, Changsheng Xu

To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only o…

Domain AdaptationUnsupervised Domain Adaptation

Source Free Unsupervised Graph Domain Adaptation

2021-12-02 · Haitao Mao, Lun Du, Yujia Zheng, Qiang Fu 외

Graph Neural Networks (GNNs) have achieved great success on a variety of tasks with graph-structural data, among which node classification is an essential one. Unsupervised Graph Domain Adaptation (UGDA) shows its practi…

Domain AdaptationGRAPH DOMAIN ADAPTATIONNode Classification

Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation

2024-03-03 · Zhen Zhang, Meihan Liu, Anhui Wang, Hongyang Chen 외

Unsupervised Graph Domain Adaptation (UGDA) has emerged as a practical solution to transfer knowledge from a label-rich source graph to a completely unlabelled target graph. However, most methods require a labelled sourc…

Contrastive LearningDomain AdaptationGRAPH DOMAIN ADAPTATION