A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

09/01/2020
by   Sicheng Zhao, et al.
7

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain. Unfortunately, direct transfer across domains often performs poorly due to the presence of domain shift or dataset bias. Domain adaptation is a machine learning paradigm that aims to learn a model from a source domain that can perform well on a different (but related) target domain. In this paper, we review the latest single-source deep unsupervised domain adaptation methods focused on visual tasks and discuss new perspectives for future research. We begin with the definitions of different domain adaptation strategies and the descriptions of existing benchmark datasets. We then summarize and compare different categories of single-source unsupervised domain adaptation methods, including discrepancy-based methods, adversarial discriminative methods, adversarial generative methods, and self-supervision-based methods. Finally, we discuss future research directions with challenges and possible solutions.

READ FULL TEXT

page 1

page 20

page 21

research
03/24/2018

Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld

Large-scale labeled training datasets have enabled deep neural networks ...
research
02/26/2020

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

In many practical applications, it is often difficult and expensive to o...
research
12/13/2021

A Survey of Unsupervised Domain Adaptation for Visual Recognition

While huge volumes of unlabeled data are generated and made available in...
research
08/15/2022

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

Deep learning has become the method of choice to tackle real-world probl...
research
10/18/2017

VisDA: The Visual Domain Adaptation Challenge

We present the 2017 Visual Domain Adaptation (VisDA) dataset and challen...
research
11/17/2022

Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey

Video analysis tasks such as action recognition have received increasing...
research
01/16/2019

A review of single-source unsupervised domain adaptation

Domain adaptation has become a prominent problem setting in machine lear...

Please sign up or login with your details

Forgot password? Click here to reset