Abstract

Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.

Original languageEnglish (US)
Article number8103149
Pages (from-to)117-129
Number of pages13
JournalIEEE Signal Processing Magazine
Volume34
Issue number6
DOIs
StatePublished - Nov 1 2017

Fingerprint

Learning Systems
Computer Vision
Computer vision
Learning systems
Transfer Learning
Neural Networks
Knowledge Transfer
Computational Model
Machine Learning
Paradigm
Learning
Deep learning
Deep neural networks

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

@article{0ffafa8844f349468424d3c689c9167c,
title = "Deep-learning systems for domain adaptation in computer vision: Learning transferable feature representations",
abstract = "Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.",
author = "{Demakethepalli Venkateswara}, Hemanth and Shayok Chakraborty and Sethuraman Panchanathan",
year = "2017",
month = "11",
day = "1",
doi = "10.1109/MSP.2017.2740460",
language = "English (US)",
volume = "34",
pages = "117--129",
journal = "IEEE Signal Processing Magazine",
issn = "1053-5888",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Deep-learning systems for domain adaptation in computer vision

T2 - Learning transferable feature representations

AU - Demakethepalli Venkateswara, Hemanth

AU - Chakraborty, Shayok

AU - Panchanathan, Sethuraman

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.

AB - Domain adaptation algorithms address the issue of transferring learning across computational models to adapt them to data from different distributions. In recent years, research in domain adaptation has been making great progress owing to the advancements in deep learning. Deep neural networks have demonstrated unrivaled success across multiple computer vision applications, including transfer learning and domain adaptation. This article outlines the latest research in domain adaptation using deep neural networks. It begins with an introduction to the concept of knowledge transfer in machine learning and the different paradigms of transfer learning. It provides a brief survey of nondeep-learning techniques and organizes the rapidly growing research in domain adaptation based on deep learning. It also highlights some drawbacks with the current state of research in this area and offers directions for future research.

UR - http://www.scopus.com/inward/record.url?scp=85040309458&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040309458&partnerID=8YFLogxK

U2 - 10.1109/MSP.2017.2740460

DO - 10.1109/MSP.2017.2740460

M3 - Article

AN - SCOPUS:85040309458

VL - 34

SP - 117

EP - 129

JO - IEEE Signal Processing Magazine

JF - IEEE Signal Processing Magazine

SN - 1053-5888

IS - 6

M1 - 8103149

ER -