We propose a novel domain adaptation framework, namely Consensus Adversarial Domain
Adaptation (CADA), that gives freedom to both target encoder and source encoder to embed …

Existing adversarial domain adaptation methods mainly consider the marginal distribution
and these methods may lead to either under transfer or negative transfer. To address this …

Adversarial learning has demonstrated good performance in the unsupervised domain
adaptation setting, by learning domain-invariant representations. However, recent work has …

Abstract Domain adaptation is crucial to adapt a learned model to new scenarios, such as
domain shifts or changing data distributions. Current approaches usually require a large …

Domain adaptation refers to the problem of leveraging labeled data in a source domain to
learn an accurate model in a target domain where labels are scarce or unavailable. A recent …

Abstract Gradual Domain Adaptation (GDA), in which the learner is provided with additional
intermediate domains, has been theoretically and empirically studied in many contexts …

Given labeled instances on a source domain and unlabeled ones on a target domain,
unsupervised domain adaptation aims to learn a task classifier that can well classify target …

Abstract Domain adaptation attempts to transfer the knowledge obtained from the source
domain to the target domain, ie, the domain where the testing data are. The main challenge …

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for
unsupervised domain adaptation in image classification, where the source and target …

Deep convolutional networks (CNNs) are able to learn robust representations and empower
many computer vision tasks such as object recognition. However, when applying CNNs to …