Search results with tag "Domain adaptation"
Unsupervised Domain Adaptation by Backpropagation
proceedings.mlr.pressadaptation approaches is the ability to learn a mapping be-tween domains in the situation when the target domain data are either fully unlabeled (unsupervised domain annota-tion) or have few labeled samples (semi-supervised domain adaptation). Below, we focus on the harder unsupervised case, although the proposed approach can be generalized to
Adversarial Discriminative Domain Adaptation
openaccess.thecvf.comdomain adaptation, as long as the latent feature space is domain invariant, and propose a discriminative approach. 3. Generalized adversarial adaptation We present a general framework for adversarial unsuper-vised adaptation methods. In unsupervised adaptation, we assume access to source images Xs and labels Ys drawn
Source-Free Domain Adaptation for Semantic Segmentation
openaccess.thecvf.comof domain shift which is caused by various data distributions in source and target domains. Unsupervised domain adaptation (UDA) [13, 54, 19, 6] for semantic segmentation has been proposed to address this issue and generalize the well-trained models on an unlabeled target domain, avoiding expensive data annotation. All the