Deep Transfer Network: Unsupervised Domain Adaptation
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 distribution of the features (marginal distribution), and the distribution of the labels given features (conditional distribution). In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process. This is achieved by two types of layers in DTN: the shared feature extraction layers which learn a shared feature subspace in which the marginal distributions of the source and the target samples are drawn close, and the discrimination layers which match conditional distributions by classifier transduction. We also show that DTN has a computation complexity linear to the number of training samples, making it suitable to large-scale problems. By combining the best paradigms in both worlds (deep neural networks in recognition, and matching marginal and conditional distributions in domain adaptation), we demonstrate by extensive experiments that DTN improves significantly over former methods in both execution time and classification accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Unsupervised Domain Adaptation Through Transferring both the Source-Knowledge and Target-Relatedness Simultaneously
Unsupervised domain adaptation (UDA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to help the learning of unlabeled target domain by transferring knowledge from the s…
BIG-bench Machine LearningDomain AdaptationUnsupervised Domain AdaptationDeep causal representation learning for unsupervised domain adaptation
Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher laye…
Domain AdaptationRepresentation LearningUnsupervised Domain AdaptationMaximizing Conditional Independence for Unsupervised Domain Adaptation
Unsupervised domain adaptation studies how to transfer a learner from a labeled source domain to an unlabeled target domain with different distributions. Existing methods mainly focus on matching the marginal distributio…
Domain AdaptationUnsupervised Domain AdaptationExploiting Local Feature Patterns for Unsupervised Domain Adaptation
Unsupervised domain adaptation methods aim to alleviate performance degradation caused by domain-shift by learning domain-invariant representations. Existing deep domain adaptation methods focus on holistic feature align…
Domain AdaptationUnsupervised Domain AdaptationTransfer Alignment Network for Double Blind Unsupervised Domain Adaptation
How can we transfer knowledge from a source domain to a target domain when each side cannot observe the data in the other side? The recent state-of-the-art deep architectures show significant performance in classificatio…
Domain AdaptationTransfer LearningUnsupervised Domain Adaptation