相关论文: Universal Domain Adaptation through Self Supervisi…

Learning to reject unknown samples (not present in the source classes) in the target domain is fairly important for unsupervised domain adaptation (UDA). There exist two typical UDA scenarios, i.e., open-set, and open-partial-set, and the…

In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize the fact that predictions from different views of the same or…

Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…

Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from…

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…

Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data by joint optimization over source data and target data.…

Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a fully-unlabeled target domain. To tackle this task, recent approaches resort to discriminative domain transfer in virtue of pseudo-labels to…

Current Domain Adaptation (DA) methods based on deep architectures assume that the source samples arise from a single distribution. However, in practice, most datasets can be regarded as mixtures of multiple domains. In these cases…

We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain. Our approach explicitly minimizes the distance between the source…

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…

We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible. We model this problem as a domain…

Domain adaptation (DA) has drawn high interests for its capacity to adapt a model trained on labeled source data to perform well on unlabeled or weakly labeled target data from a different domain. Most common DA techniques require the…

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 approach for finding a common representation of the two…

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…

Training models dedicated to semantic segmentation requires a large amount of pixel-wise annotated data. Due to their costly nature, these annotations might not be available for the task at hand. To alleviate this problem, unsupervised…

Recognition across domains has recently become an active topic in the research community. However, it has been largely overlooked in the problem of recognition in new unseen domains. Under this condition, the delivered deep network models…

Unsupervised domain adaptation enables intelligent models to transfer knowledge from a labeled source domain to a similar but unlabeled target domain. Recent study reveals that knowledge can be transferred from one source domain to another…

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 amount of labeled or unlabeled data from the shifted domain. This can…

Domain adaptation addresses the problem created when training data is generated by a so-called source distribution, but test data is generated by a significantly different target distribution. In this work, we present approximate label…

Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…