Tackling unsupervised multi-source domain adaptation with optimism and consistency
It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to adjust the mixture distribution weights remains an open question. Moreover, most existing work on this topic focuses only on minimizing the error on the source domains and achieving domain-invariant representations, which is insufficient to ensure low error on the target domain. In this work, we present a novel framework that addresses both problems and beats the current state of the art by using a mildly optimistic objective function and consistency regularization on the target samples.
Code (1)
Tasks
Domain AdaptationOpen-Ended Question AnsweringSimilar Papers 제목 키워드 기반
Unsupervised Domain Adaptation Using Compact Internal Representations
A major technique for tackling unsupervised domain adaptation involves mapping data points from both the source and target domains into a shared embedding space. The mapping encoder to the embedding space is trained such…
Domain AdaptationUnsupervised Domain AdaptationSource-Free Unsupervised Domain Adaptation: A Survey
Unsupervised domain adaptation (UDA) via deep learning has attracted appealing attention for tackling domain-shift problems caused by distribution discrepancy across different domains. Existing UDA approaches highly depe…
Domain AdaptationSurveySystematic Literature ReviewTransfer Learning+1GrabDAE: An Innovative Framework for Unsupervised Domain Adaptation Utilizing Grab-Mask and Denoise Auto-Encoder
Unsupervised Domain Adaptation (UDA) aims to adapt a model trained on a labeled source domain to an unlabeled target domain by addressing the domain shift. Existing Unsupervised Domain Adaptation (UDA) methods often fall…
Contrastive LearningDenoisingDomain AdaptationUnsupervised Domain AdaptationSample-to-Sample Correspondence for Unsupervised Domain Adaptation
The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training…
Domain AdaptationGeneral Classificationimage-classificationImage Classification+3Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
We consider the problem of unsupervised domain adaptation for semantic segmentation by easing the domain shift between the source domain (synthetic data) and the target domain (real data) in this work. State-of-the-art a…
Domain AdaptationSemantic SegmentationUnsupervised Domain Adaptation