A Theory of Output-Side Unsupervised Domain Adaptation

2017-03-05 · Tomer Galanti, Lior Wolf

When learning a mapping from an input space to an output space, the assumption that the sample distribution of the training data is the same as that of the test data is often violated. Unsupervised domain shift methods adapt the learned function in order to correct for this shift. Previous work has focused on utilizing unlabeled samples from the target distribution. We consider the complementary problem in which the unlabeled samples are given post mapping, i.e., we are given the outputs of the mapping of unknown samples from the shifted domain. Two other variants are also studied: the two sided version, in which unlabeled samples are give from both the input and the output spaces, and the Domain Transfer problem, which was recently formalized. In all cases, we derive generalization bounds that employ discrepancy terms.

📄 PDF Abstract BibTeX arXiv:1703.01606

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationGeneralization BoundsUnsupervised Domain Adaptation

f-Domain-Adversarial Learning: Theory and Algorithms for Unsupervised Domain Adaptation with Neural Networks

2021-01-01 · David Acuna, Guojun Zhang, Marc T Law, Sanja Fidler

The problem of unsupervised domain adaptation arises in a variety of practical applications where the distribution of the training samples differs from those used at test time. The existing theory of domain adaptation de…

Domain Adaptation Generalization Bounds Learning Theory Unsupervised Domain Adaptation

Unsupervised Domain Adaptation for the Histopathological Cell Segmentation through Self-Ensembling

2021-07-20 · MICCAI Workshop COMPAY 2021 9 · CHAOQUN LI, Yitian Zhou, TangQi Shi, Yenan Wu 외

Histopathological images are generally considered as the golden standard for clinical diagnosis and cancer grading. Accurate segmentation of cells/nuclei from histopathological images is a critical step to obtain reliabl…

Cell Segmentation Domain Adaptation Segmentation Unsupervised Domain Adaptation

Label Alignment Regularization for Distribution Shift

2022-11-27 · Ehsan Imani, Guojun Zhang, Runjia Li, Jun Luo 외

Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix. Drawing inspi…

Domain Adaptation Representation Learning Sentiment Analysis Unsupervised Domain Adaptation

Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm

2025-11-14 · Fuxiang Huang, Xiaowei Fu, Shiyu Ye, Lina Ma 외 arxiv

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overloo…

Unsupervised Domain Adaptation Adversarial Robustness

Learning from a Complementary-label Source Domain: Theory and Algorithms

2020-08-04 · Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan 외

In unsupervised domain adaptation (UDA), a classifier for the target domain is trained with massive true-label data from the source domain and unlabeled data from the target domain. However, collecting fully-true-label d…

Domain Adaptation Unsupervised Domain Adaptation