Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

  title={Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives},
  author={Xiaofeng Liu and Chaehwa Yoo and Fangxu Xing and Hyejin Oh and Georges El Fakhri and Je-Won Kang and Jonghye Woo},
Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed… 

Figures and Tables from this paper

Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance

A probabilistic framework is defined and a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors is presented, applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains.

ACT: Semi-supervised Domain-adaptive Medical Image Segmentation with Asymmetric Co-training

This work proposes to exploit both labeled source and target domain data, in addition to unlabeled target data in a unified manner, and presents a novel asymmetric co-training (ACT) framework to integrate these subsets and avoid the domination of the source domain data.

Cross Domain Data Generation for Smart Building Fault Detection and Diagnosis

A novel Adversarial Cross domain Data Generation (ACDG) framework to impute missing fault data for building fault detection and diagnosis where labeled data is costly is proposed and tested with the real-world Air handling unit fault dataset of the ASHRAE Research Project 1312.



A Survey of Unsupervised Deep Domain Adaptation

A survey will compare single-source and typically homogeneous unsupervised deep domain adaptation approaches, combining the powerful, hierarchical representations from deep learning with domain adaptation to reduce reliance on potentially costly target data labels.

Adaptive Batch Normalization for practical domain adaptation

Semi-supervised Domain Adaptation with Subspace Learning for visual recognition

A novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant low-dimensional structures across domains to correct data distribution mismatch and leverages available unlabeled target examples to exploit the underlying intrinsic information in the target domain.

Unsupervised Domain Adaptation by Backpropagation

The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-of-the-art on Office datasets.

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

This survey defines various MDA strategies and summarize available datasets for evaluation, and compares modern MDA methods in the deep learning era, including latent space transformation and intermediate domain generation.

Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld

This paper summarizes and compares the latest unsupervised domain adaptation methods in computer vision applications, and classifies the non-deep approaches into sample re-weighting and intermediate subspace transformation categories, while the deep strategy includes discrepancy-based methods, adversarial generative models, adversaria discriminative models and reconstruction- based methods.

Revisiting Batch Normalization For Practical Domain Adaptation

This paper proposes a simple yet powerful remedy, called Adaptive Batch Normalization (AdaBN) to increase the generalization ability of a DNN, and demonstrates that the method is complementary with other existing methods and may further improve model performance.

Boosting Domain Adaptation by Discovering Latent Domains

A novel Convolutional Neural Network (CNN) architecture is introduced which automatically discovers latent domains in visual datasets and exploits this information to learn robust target classifiers and outperforms state-of-the-art multi-source DA methods by a large margin.

DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation

Through a measure of discrepancy on joint deep representations/labels based on optimal transport, this work not only learns new data representations aligned between the source and target domain, but also simultaneously preserve the discriminative information used by the classifier.

A Survey of Unsupervised Domain Adaptation for Visual Recognition

The principal objective of UDA is to reduce the domain discrepancy between the labeled source data and unlabeled target data and to learn domain-invariant representations across the two domains during training.