Unsupervised Domain Adaptation

256 papers with code • 13 benchmarks • 13 datasets

Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.

Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

Greatest papers with code

Importance Weighted Adversarial Nets for Partial Domain Adaptation

thuml/Transfer-Learning-Library CVPR 2018

This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain.

Partial Domain Adaptation Transfer Learning +1

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

thuml/Transfer-Learning-Library CVPR 2018

To solve these problems, we introduce a new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries.

Image Classification Semantic Segmentation +1

Unsupervised Domain Adaptation by Backpropagation

thuml/Transfer-Learning-Library 26 Sep 2014

Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary).

Image Classification Multi-target Domain Adaptation +3

Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification

yxgeee/MMT ICLR 2020

In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.

Clustering Unsupervised Domain Adaptation +1

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification

yxgeee/MMT CVPR 2018

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e. g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network.

Person Re-Identification Unsupervised Domain Adaptation

Adversarial Discriminative Domain Adaptation

corenel/pytorch-adda CVPR 2017

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains.

General Classification Object Classification +2

Domain Adaptive Ensemble Learning

KaiyangZhou/Dassl.pytorch 16 Mar 2020

Each such classifier is an expert to its own domain and a non-expert to others.

Domain Generalization Ensemble Learning +1

Improve Unsupervised Domain Adaptation with Mixup Training

facebookresearch/DomainBed 3 Jan 2020

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.

Activity Recognition Image Classification +1

Reducing Domain Gap by Reducing Style Bias

facebookresearch/DomainBed 25 Oct 2019

Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift.

Domain Generalization Unsupervised Domain Adaptation