Deep Clustering for Domain Adaptation

Boyan Gao; Yongxin Yang; Henry Gouk; Timothy M. Hospedales

doi:10.1109/ICASSP40776.2020.9053622

Deep Clustering for Domain Adaptation

Boyan Gao, Yongxin Yang, Henry Gouk, Timothy M. Hospedales

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We address the heterogeneous domain adaptation task: adapting a classifier trained on data from one domain to operate on another domain that also has a different label space. We consider two settings that both exhibit label scarcity of some
form—one where only unlabelled data is available, and another where a small volume of labelled data is available in addition to the unlabelled data. Our method is based on two specialisations of a recently proposed approach for deep clustering.
It is shown that our approach noticeably outperforms other methods based on deep clustering in both the fully unsupervised and the semi-supervised settings.

Original language	English
Title of host publication	ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	Institute of Electrical and Electronics Engineers
Pages	4247-4251
Number of pages	5
ISBN (Electronic)	978-1-5090-6631-5
ISBN (Print)	978-1-5090-6632-2
DOIs	https://doi.org/10.1109/ICASSP40776.2020.9053622
Publication status	Published - 14 May 2020
Event	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing - Barcelona, Spain Duration: 4 May 2020 → 8 May 2020 Conference number: 45

Publication series

Name
Publisher	IEEE
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP 2020
Country/Territory	Spain
City	Barcelona
Period	4/05/20 → 8/05/20

Access to Document

10.1109/ICASSP40776.2020.9053622Licence: All Rights Reserved

Deep Clustering for Domain_GAO_DOA24112020_AFVAccepted author manuscript, 177 KB

https://ieeexplore.ieee.org/document/9053622Licence: All Rights Reserved

Signal Processing in the Information Age
Davies, M., Hopgood, J., Hospedales, T., Mulgrew, B., Thompson, J., Tsaftaris, S. & Yaghoobi Vaighan, M.
EPSRC
1/07/18 → 31/03/24
Project: Research

Cite this

@inproceedings{ffc3b7ac6f30441ba21576a1838f5fbd,

title = "Deep Clustering for Domain Adaptation",

abstract = "We address the heterogeneous domain adaptation task: adapting a classifier trained on data from one domain to operate on another domain that also has a different label space. We consider two settings that both exhibit label scarcity of someform—one where only unlabelled data is available, and another where a small volume of labelled data is available in addition to the unlabelled data. Our method is based on two specialisations of a recently proposed approach for deep clustering.It is shown that our approach noticeably outperforms other methods based on deep clustering in both the fully unsupervised and the semi-supervised settings.",

author = "Boyan Gao and Yongxin Yang and Henry Gouk and Hospedales, {Timothy M.}",

year = "2020",

month = may,

day = "14",

doi = "10.1109/ICASSP40776.2020.9053622",

language = "English",

isbn = "978-1-5090-6632-2",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "4247--4251",

booktitle = "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

address = "United States",

note = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",

}

Gao, B, Yang, Y, Gouk, H & Hospedales, TM 2020, Deep Clustering for Domain Adaptation. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 4247-4251, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053622

TY - GEN

T1 - Deep Clustering for Domain Adaptation

AU - Gao, Boyan

AU - Yang, Yongxin

AU - Gouk, Henry

AU - Hospedales, Timothy M.

N1 - Conference code: 45

PY - 2020/5/14

Y1 - 2020/5/14

N2 - We address the heterogeneous domain adaptation task: adapting a classifier trained on data from one domain to operate on another domain that also has a different label space. We consider two settings that both exhibit label scarcity of someform—one where only unlabelled data is available, and another where a small volume of labelled data is available in addition to the unlabelled data. Our method is based on two specialisations of a recently proposed approach for deep clustering.It is shown that our approach noticeably outperforms other methods based on deep clustering in both the fully unsupervised and the semi-supervised settings.

AB - We address the heterogeneous domain adaptation task: adapting a classifier trained on data from one domain to operate on another domain that also has a different label space. We consider two settings that both exhibit label scarcity of someform—one where only unlabelled data is available, and another where a small volume of labelled data is available in addition to the unlabelled data. Our method is based on two specialisations of a recently proposed approach for deep clustering.It is shown that our approach noticeably outperforms other methods based on deep clustering in both the fully unsupervised and the semi-supervised settings.

U2 - 10.1109/ICASSP40776.2020.9053622

DO - 10.1109/ICASSP40776.2020.9053622

M3 - Conference contribution

SN - 978-1-5090-6632-2

SP - 4247

EP - 4251

BT - ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - Institute of Electrical and Electronics Engineers

T2 - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 4 May 2020 through 8 May 2020

ER -

Deep Clustering for Domain Adaptation

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

Signal Processing in the Information Age

Cite this