Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation

•We design a discriminative embedding constraint for the heterogeneous domain adaptation problem, which enhances the discriminative power of the common subspace.•To the best of our knowledge, we are the first to integrate the classifier adaptation, distribution alignment, and discriminative embeddin...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Pattern recognition Ročník 101; s. 107165
Hlavní autoři: Yao, Yuan, Zhang, Yu, Li, Xutao, Ye, Yunming
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.05.2020
Témata:
ISSN:0031-3203, 1873-5142
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •We design a discriminative embedding constraint for the heterogeneous domain adaptation problem, which enhances the discriminative power of the common subspace.•To the best of our knowledge, we are the first to integrate the classifier adaptation, distribution alignment, and discriminative embedding constraints into a unified framework.•Many loss (e.g., cross-entropy loss or squared loss) and projection (e.g., linear projection or non-linear projection) functions can be incorporated into the proposed Discriminative Distribution Alignment framework. Two approaches are developed by using the cross-entropy loss and the squared loss, respectively.•Extensive experimental results are reported on the tasks of categorization across domains and modalities, which demonstrate the effectiveness of the proposed Discriminative Distribution Alignment framework. Heterogeneous domain adaptation (HDA) aims to leverage knowledge from a source domain for helping learn an accurate model in a heterogeneous target domain. HDA is exceedingly challenging since the feature spaces of domains are distinct. To tackle this issue, we propose a unified learning framework called Discriminative Distribution Alignment (DDA) for deriving a domain-invariant subspace. The proposed DDA can simultaneously match the discriminative directions of domains, align the distributions across domains, and enhance the separability of data during adaptation. To achieve this, DDA trains an adaptive classifier by both reducing the distribution divergence and enlarging distances between class centroids. Based on the proposed DDA framework, we further develop two methods, by embedding the cross-entropy loss and squared loss into this framework, respectively. We conduct experiments on the tasks of categorization across domains and modalities. Experimental results clearly demonstrate that the proposed DDA outperforms several state-of-the-art models.
AbstractList •We design a discriminative embedding constraint for the heterogeneous domain adaptation problem, which enhances the discriminative power of the common subspace.•To the best of our knowledge, we are the first to integrate the classifier adaptation, distribution alignment, and discriminative embedding constraints into a unified framework.•Many loss (e.g., cross-entropy loss or squared loss) and projection (e.g., linear projection or non-linear projection) functions can be incorporated into the proposed Discriminative Distribution Alignment framework. Two approaches are developed by using the cross-entropy loss and the squared loss, respectively.•Extensive experimental results are reported on the tasks of categorization across domains and modalities, which demonstrate the effectiveness of the proposed Discriminative Distribution Alignment framework. Heterogeneous domain adaptation (HDA) aims to leverage knowledge from a source domain for helping learn an accurate model in a heterogeneous target domain. HDA is exceedingly challenging since the feature spaces of domains are distinct. To tackle this issue, we propose a unified learning framework called Discriminative Distribution Alignment (DDA) for deriving a domain-invariant subspace. The proposed DDA can simultaneously match the discriminative directions of domains, align the distributions across domains, and enhance the separability of data during adaptation. To achieve this, DDA trains an adaptive classifier by both reducing the distribution divergence and enlarging distances between class centroids. Based on the proposed DDA framework, we further develop two methods, by embedding the cross-entropy loss and squared loss into this framework, respectively. We conduct experiments on the tasks of categorization across domains and modalities. Experimental results clearly demonstrate that the proposed DDA outperforms several state-of-the-art models.
ArticleNumber 107165
Author Ye, Yunming
Li, Xutao
Yao, Yuan
Zhang, Yu
Author_xml – sequence: 1
  givenname: Yuan
  surname: Yao
  fullname: Yao, Yuan
  organization: Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
– sequence: 2
  givenname: Yu
  surname: Zhang
  fullname: Zhang, Yu
  organization: Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
– sequence: 3
  givenname: Xutao
  surname: Li
  fullname: Li, Xutao
  organization: Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
– sequence: 4
  givenname: Yunming
  orcidid: 0000-0002-3581-9476
  surname: Ye
  fullname: Ye, Yunming
  email: yeyunming@hit.edu.cn
  organization: Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China
BookMark eNqFkE1LAzEQhoNUsK3-Aw_7B7Ymm81-9CCU-gmCF70assmkTm2TkqQV_71b1pMHPQ3M8LzM-0zIyHkHhFwyOmOUVVfr2U4l7VezgrK2X9WsEidkzJqa54KVxYiMKeUs5wXlZ2QS45pSVveHMXm7wagDbtGphAfIDMYUsNsn9C5TG1y5Lbg0zxbZ3qFFMJkNagufPnxk1ofsHRIEvwIHfh8z47cKe86oXVLHiHNyatUmwsXPnJLXu9uX5UP-9Hz_uFw85ZrTKuVQNK1iHYfC0LYRvOqE4nVd1JYVwjJhRFWZsu14w6wF2tfovwfBoSrromSGT0k55OrgYwxg5a4vpcKXZFQeHcm1HBzJoyM5OOqx-S9M4_B4Cgo3_8HXAwx9sQNCkFEjOA0GA-gkjce_A74BjjGIMg
CitedBy_id crossref_primary_10_1007_s10044_024_01390_w
crossref_primary_10_1007_s10489_022_03296_8
crossref_primary_10_1016_j_patcog_2024_110473
crossref_primary_10_1093_bib_bbae004
crossref_primary_10_1016_j_neunet_2023_11_048
crossref_primary_10_1109_JIOT_2024_3457894
crossref_primary_10_1109_TNNLS_2024_3372004
crossref_primary_10_1145_3469856
crossref_primary_10_1155_2022_8884669
crossref_primary_10_1109_JIOT_2023_3239872
crossref_primary_10_1109_JIOT_2022_3218339
crossref_primary_10_1016_j_patcog_2024_110857
crossref_primary_10_1016_j_patcog_2022_108955
crossref_primary_10_1109_TGRS_2024_3502236
crossref_primary_10_1016_j_knosys_2023_111092
crossref_primary_10_1109_TASLP_2023_3288415
crossref_primary_10_1109_TNNLS_2025_3563618
crossref_primary_10_1016_j_ins_2024_121836
crossref_primary_10_1007_s10489_021_02756_x
crossref_primary_10_1016_j_patcog_2024_110409
crossref_primary_10_1109_TMM_2024_3411316
crossref_primary_10_1016_j_patcog_2021_108362
crossref_primary_10_1016_j_ymssp_2022_108853
crossref_primary_10_1016_j_knosys_2022_108443
crossref_primary_10_1080_24725854_2024_2405089
crossref_primary_10_1109_TCYB_2021_3070545
crossref_primary_10_1145_3544105
crossref_primary_10_1080_00207543_2021_1989076
crossref_primary_10_1007_s00521_024_09786_9
crossref_primary_10_1007_s13198_024_02684_2
crossref_primary_10_1016_j_jnca_2023_103760
crossref_primary_10_1007_s10994_024_06566_3
crossref_primary_10_1109_LGRS_2022_3175056
crossref_primary_10_1109_TNNLS_2021_3105868
crossref_primary_10_1007_s13042_022_01646_z
Cites_doi 10.1016/j.patcog.2018.04.027
10.1016/j.patcog.2017.04.011
10.1090/S0025-5718-1980-0572855-7
10.1186/s40537-017-0089-0
10.1109/TPAMI.2013.167
10.1016/j.patcog.2018.03.005
10.1007/978-3-319-58347-1_1
10.1109/TPAMI.2014.2343216
10.1109/TPAMI.2018.2824309
10.1007/BF01589116
10.1007/s11263-014-0719-3
10.1016/j.patrec.2018.02.011
ContentType Journal Article
Copyright 2020 Elsevier Ltd
Copyright_xml – notice: 2020 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.patcog.2019.107165
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1873-5142
ExternalDocumentID 10_1016_j_patcog_2019_107165
S0031320319304650
GroupedDBID --K
--M
-D8
-DT
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29O
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABFRF
ABHFT
ABJNI
ABMAC
ABTAH
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADMXK
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FD6
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
G8K
GBLVA
GBOLZ
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
KZ1
LG9
LMP
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
VOH
WUQ
XJE
XPP
ZMT
ZY4
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-e289a1b3e2d098536b5a37727f125f15d566d49b381ffe0203714e53e647241d3
ISICitedReferencesCount 40
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000525824600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0031-3203
IngestDate Sat Nov 29 07:29:43 EST 2025
Tue Nov 18 21:01:58 EST 2025
Fri Feb 23 02:49:10 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Classifier adaptation
Discriminative embedding
Heterogeneous domain adaptation
Subspace learning
Distribution alignment
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-e289a1b3e2d098536b5a37727f125f15d566d49b381ffe0203714e53e647241d3
ORCID 0000-0002-3581-9476
ParticipantIDs crossref_primary_10_1016_j_patcog_2019_107165
crossref_citationtrail_10_1016_j_patcog_2019_107165
elsevier_sciencedirect_doi_10_1016_j_patcog_2019_107165
PublicationCentury 2000
PublicationDate May 2020
2020-05-00
PublicationDateYYYYMMDD 2020-05-01
PublicationDate_xml – month: 05
  year: 2020
  text: May 2020
PublicationDecade 2020
PublicationTitle Pattern recognition
PublicationYear 2020
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Li, Jing, Lu, Zhu, Shen (bib0038) 2019; 28
Yang, Ma, Yuen (bib0012) 2018; 81
Yan, Li, Ng, Tan, Wu, Min, Wu (bib0035) 2017
Nocedal (bib0050) 1980; 35
Zhou, Tsang, Pan, Tan (bib0032) 2014
Griffin, Holub, Perona (bib0054) 2007
G. Csurka, A Comprehensive Survey on Domain Adaptation for Visual Applications, Springer International Publishing, pp. 1–35.
Day, Khoshgoftaar (bib0004) 2017; 4
Wang, Feng, Chen, Yu, Huang, Yu (bib0014) 2018
Gretton, Borgwardt, Rasch, Schölkopf, Smola (bib0048) 2007
Yan, Li, Wu, Min, Tan, Wu (bib0047) 2018
Ye, Sheng, Zhan, He (bib0046) 2018
Le, Ngiam, Coates, Lahiri, Prochnow, Ng (bib0052) 2011
Bousmalis, Trigeorgis, Silberman, Krishnan, Erhan (bib0020) 2016
Luo, Wen, Liu, Tao (bib0044) 2019; 41
Kulis, Saenko, Darrell (bib0029) 2011
Villani (bib0045) 2008
Zhang, Li, Ogunbona (bib0009) 2017
Yao, Pan, Ngo, Li, Mei (bib0010) 2015
Saenko, Kulis, Fritz, Darrell (bib0053) 2010
Long, Cao, Cao, Wang, Jordan (bib0021) 2018
Zhu, Chen, Lu, Pan, Xue, Yu, Yang (bib0011) 2011
Chen, Hsu, Tsai, Wang, Chen (bib0042) 2016
Donahue, Jia, Vinyals, Hoffman, Zhang, Tzeng, Darrell (bib0057) 2014
Cao, Long, Wang (bib0022) 2018
Wang, Mahadevan (bib0025) 2011
Vapnik (bib0049) 1998
Xiao, Guo (bib0017) 2015; 37
Weiss, Khoshgoftaar, Wang (bib0002) 2016; 3
Hoffman, Rodner, Donahue, Kulis, Saenko (bib0031) 2014; 109
Tsai, Yeh, Wang (bib0034) 2016
Li, Duan, Xu, Tsang (bib0027) 2014; 36
Long, Zhu, Wang, Jordan (bib0007) 2017
Liu, Nocedal (bib0051) 1989; 45
Fang, Chiang (bib0037) 2018; 106
van der Maaten (bib0058) 2014
Bay, Tuytelaars, Gool (bib0056) 2006
Li, Lu, Huang, Zhu, Shen (bib0040) 2019; 49
Duan, Xu, Tsang (bib0026) 2012
Zhou, Bousquet, Lal, Weston, Schölkopf (bib0039) 2004
Hsieh, Tao, Tsai, Yeh, Wang (bib0028) 2016
Xiao, Guo (bib0016) 2015
Long, Cao, Wang, Jordan (bib0006) 2015
Shi, Liu, Fan, Yu, Zhu (bib0024) 2010
Pereira, Torres (bib0008) 2018; 75
Li, Wang, Shi, Hou, Liu (bib0015) 2018; 80
Tan, Zhang, Pan, Yang (bib0013) 2017
Li, Pan, Wan, Kot (bib0043) 2019
Long, Wang, Ding, Sun, Yu (bib0005) 2013
Hoffman, Rodner, Donahue, Saenko, Darrell (bib0030) 2013
Tsai, Yeh, Wang (bib0033) 2016
Ding, Nasrabadi, Fu (bib0023) 2018; 27
Li, Lu, Huang, Zhu, Shen (bib0036) 2018
Shu, Qi, Tang, Wang (bib0041) 2015
Amini, Usunier, Goutte (bib0055) 2009
Long, Wang, Ding, Pan, Yu (bib0019) 2014; 26
Pan, Yang (bib0001) 2010; 22
Tan, Song, Zhong, Yang (bib0018) 2015
Ding (10.1016/j.patcog.2019.107165_bib0023) 2018; 27
Li (10.1016/j.patcog.2019.107165_bib0038) 2019; 28
Li (10.1016/j.patcog.2019.107165_bib0040) 2019; 49
Amini (10.1016/j.patcog.2019.107165_bib0055) 2009
Villani (10.1016/j.patcog.2019.107165_bib0045) 2008
Yang (10.1016/j.patcog.2019.107165_bib0012) 2018; 81
van der Maaten (10.1016/j.patcog.2019.107165_bib0058) 2014
Zhou (10.1016/j.patcog.2019.107165_bib0039) 2004
Yan (10.1016/j.patcog.2019.107165_bib0035) 2017
Weiss (10.1016/j.patcog.2019.107165_bib0002) 2016; 3
Long (10.1016/j.patcog.2019.107165_bib0006) 2015
Chen (10.1016/j.patcog.2019.107165_bib0042) 2016
Nocedal (10.1016/j.patcog.2019.107165_bib0050) 1980; 35
Hoffman (10.1016/j.patcog.2019.107165_bib0030) 2013
Zhou (10.1016/j.patcog.2019.107165_bib0032) 2014
Tan (10.1016/j.patcog.2019.107165_bib0013) 2017
Luo (10.1016/j.patcog.2019.107165_bib0044) 2019; 41
Hsieh (10.1016/j.patcog.2019.107165_bib0028) 2016
Zhu (10.1016/j.patcog.2019.107165_bib0011) 2011
Li (10.1016/j.patcog.2019.107165_bib0036) 2018
Kulis (10.1016/j.patcog.2019.107165_bib0029) 2011
Pereira (10.1016/j.patcog.2019.107165_bib0008) 2018; 75
Tsai (10.1016/j.patcog.2019.107165_bib0033) 2016
Shu (10.1016/j.patcog.2019.107165_sbref0040) 2015
Shi (10.1016/j.patcog.2019.107165_bib0024) 2010
Long (10.1016/j.patcog.2019.107165_bib0019) 2014; 26
Long (10.1016/j.patcog.2019.107165_sbref0020) 2018
Bay (10.1016/j.patcog.2019.107165_bib0056) 2006
Yan (10.1016/j.patcog.2019.107165_bib0047) 2018
Wang (10.1016/j.patcog.2019.107165_bib0014) 2018
Cao (10.1016/j.patcog.2019.107165_bib0022) 2018
Long (10.1016/j.patcog.2019.107165_bib0007) 2017
Tsai (10.1016/j.patcog.2019.107165_bib0034) 2016
Griffin (10.1016/j.patcog.2019.107165_bib0054) 2007
Zhang (10.1016/j.patcog.2019.107165_bib0009) 2017
Xiao (10.1016/j.patcog.2019.107165_bib0017) 2015; 37
Gretton (10.1016/j.patcog.2019.107165_bib0048) 2007
Vapnik (10.1016/j.patcog.2019.107165_bib0049) 1998
Xiao (10.1016/j.patcog.2019.107165_bib0016) 2015
Day (10.1016/j.patcog.2019.107165_bib0004) 2017; 4
10.1016/j.patcog.2019.107165_bib0003
Saenko (10.1016/j.patcog.2019.107165_bib0053) 2010
Tan (10.1016/j.patcog.2019.107165_bib0018) 2015
Pan (10.1016/j.patcog.2019.107165_bib0001) 2010; 22
Ye (10.1016/j.patcog.2019.107165_bib0046) 2018
Li (10.1016/j.patcog.2019.107165_bib0043) 2019
Li (10.1016/j.patcog.2019.107165_bib0027) 2014; 36
Yao (10.1016/j.patcog.2019.107165_bib0010) 2015
Duan (10.1016/j.patcog.2019.107165_bib0026) 2012
Hoffman (10.1016/j.patcog.2019.107165_bib0031) 2014; 109
Long (10.1016/j.patcog.2019.107165_bib0005) 2013
Li (10.1016/j.patcog.2019.107165_bib0015) 2018; 80
Bousmalis (10.1016/j.patcog.2019.107165_bib0020) 2016
Wang (10.1016/j.patcog.2019.107165_bib0025) 2011
Liu (10.1016/j.patcog.2019.107165_bib0051) 1989; 45
Donahue (10.1016/j.patcog.2019.107165_bib0057) 2014
Fang (10.1016/j.patcog.2019.107165_bib0037) 2018; 106
Le (10.1016/j.patcog.2019.107165_bib0052) 2011
References_xml – volume: 45
  start-page: 503
  year: 1989
  end-page: 528
  ident: bib0051
  article-title: On the limited memory bfgs method for large scale optimization
  publication-title: Math. Program.
– start-page: 265
  year: 2011
  end-page: 272
  ident: bib0052
  article-title: On optimization methods for deep learning
  publication-title: ICML
– start-page: 5150
  year: 2017
  end-page: 5158
  ident: bib0009
  article-title: Joint geometrical and statistical alignment for visual domain adaptation
  publication-title: CVPR
– start-page: 2842
  year: 2016
  end-page: 2846
  ident: bib0034
  article-title: Heterogeneous domain adaptation with label and structure consistency
  publication-title: ICASSP
– start-page: 213
  year: 2010
  end-page: 226
  ident: bib0053
  article-title: Adapting visual category models to new domains
  publication-title: ECCV
– year: 2008
  ident: bib0045
  publication-title: Optimal Transport: Old and New
– start-page: 404
  year: 2006
  end-page: 417
  ident: bib0056
  article-title: Surf: Speeded up robust features
  publication-title: ECCV
– volume: 75
  start-page: 235
  year: 2018
  end-page: 249
  ident: bib0008
  article-title: Semi-supervised transfer subspace for domain adaptation
  publication-title: Pattern Recognit.
– start-page: 1541
  year: 2011
  end-page: 1546
  ident: bib0025
  article-title: Heterogeneous domain adaptation using manifold alignment
  publication-title: IJCAI
– start-page: 2142
  year: 2015
  end-page: 2150
  ident: bib0010
  article-title: Semi-supervised domain adaptation with subspace learning for visual recognition
  publication-title: CVPR
– year: 1998
  ident: bib0049
  publication-title: Statistical Learning Theory
– start-page: 2604
  year: 2017
  end-page: 2610
  ident: bib0013
  article-title: Distant domain transfer learning
  publication-title: AAAI
– start-page: 28
  year: 2009
  end-page: 36
  ident: bib0055
  article-title: Learning from multiple partially observed views - an application to multilingual text categorization
  publication-title: NeurIPS
– volume: 81
  start-page: 615
  year: 2018
  end-page: 632
  ident: bib0012
  article-title: Learning domain-shared group-sparse representation for unsupervised domain adaptation
  publication-title: Pattern Recognit.
– volume: 27
  start-page: 5214
  year: 2018
  end-page: 5224
  ident: bib0023
  article-title: Semi-supervised deep domain adaptation via coupled neural networks
  publication-title: TIP
– start-page: 2969
  year: 2018
  end-page: 2975
  ident: bib0047
  article-title: Semi-supervised optimal transport for heterogeneous domain adaptation
  publication-title: IJCAI
– start-page: 5081
  year: 2016
  end-page: 5090
  ident: bib0033
  article-title: Learning cross-domain landmarks for heterogeneous domain adaptation
  publication-title: CVPR
– year: 2016
  ident: bib0042
  article-title: Transfer neural trees for heterogeneous domain adaptation
  publication-title: ECCV
– volume: 106
  start-page: 13
  year: 2018
  end-page: 19
  ident: bib0037
  article-title: A discriminative feature mapping approach to heterogeneous domain adaptation
  publication-title: Pattern Recognit. Lett.
– start-page: 711
  year: 2012
  end-page: 718
  ident: bib0026
  article-title: Learning with augmented features for heterogeneous domain adaptation
  publication-title: ICML
– year: 2007
  ident: bib0054
  publication-title: Technical Report 7694
– start-page: 2208
  year: 2017
  end-page: 2217
  ident: bib0007
  article-title: Deep transfer learning with joint adaptation networks
  publication-title: ICML
– start-page: 525
  year: 2015
  end-page: 540
  ident: bib0016
  article-title: Semi-supervised subspace co-projection for multi-class heterogeneous domain adaptation
  publication-title: ECML PKDD
– start-page: 1304
  year: 2011
  end-page: 1309
  ident: bib0011
  article-title: Heterogeneous transfer learning for image classification
  publication-title: AAAI
– start-page: 1785
  year: 2011
  end-page: 1792
  ident: bib0029
  article-title: What you saw is not what you get: domain adaptation using asymmetric kernel transforms
  publication-title: CVPR
– start-page: 1095
  year: 2014
  end-page: 1103
  ident: bib0032
  article-title: Heterogeneous domain adaptation for multiple classes
  publication-title: AISTATS
– start-page: 321
  year: 2004
  end-page: 328
  ident: bib0039
  article-title: Learning with local and global consistency
  publication-title: NeurIPS
– start-page: 3221
  year: 2014
  end-page: 3245
  ident: bib0058
  article-title: Accelerating t-SNE using tree-based algorithms
  publication-title: JMLR
– start-page: 35
  year: 2015
  end-page: 44
  ident: bib0041
  article-title: Weakly-shared deep transfer networks for heterogeneous-domain knowledge propagation
  publication-title: ACM MM
– start-page: 1155
  year: 2015
  end-page: 1164
  ident: bib0018
  article-title: Transitive transfer learning
  publication-title: KDD
– year: 2013
  ident: bib0030
  article-title: Efficient learning of domain-invariant image representations
  publication-title: ICLR
– start-page: 8602
  year: 2019
  end-page: 8609
  ident: bib0043
  article-title: Heterogeneous transfer learning via deep matrix completion with adversarial kernel embedding
  publication-title: AAAI
– volume: 41
  start-page: 1013
  year: 2019
  end-page: 1026
  ident: bib0044
  article-title: Transferring knowledge fragments for learning distance metric from a heterogeneous domain
  publication-title: TPAMI
– volume: 35
  start-page: 773
  year: 1980
  end-page: 782
  ident: bib0050
  article-title: Updating Quasi-Newton matrices with limited storage
  publication-title: Math. Comput.
– reference: G. Csurka, A Comprehensive Survey on Domain Adaptation for Visual Applications, Springer International Publishing, pp. 1–35.
– start-page: 2200
  year: 2013
  end-page: 2207
  ident: bib0005
  article-title: Transfer feature learning with joint distribution adaptation
  publication-title: ICCV
– volume: 37
  start-page: 54
  year: 2015
  end-page: 66
  ident: bib0017
  article-title: Feature space independent semi-supervised domain adaptation via kernel matching
  publication-title: TPAMI
– volume: 80
  start-page: 109
  year: 2018
  end-page: 117
  ident: bib0015
  article-title: Adaptive batch normalization for practical domain adaptation
  publication-title: Pattern Recognit.
– start-page: 3252
  year: 2017
  end-page: 3258
  ident: bib0035
  article-title: Learning discriminative correlation subspace for heterogeneous domain adaptation
  publication-title: IJCAI
– volume: 22
  start-page: 1345
  year: 2010
  end-page: 1359
  ident: bib0001
  article-title: A survey on transfer learning
  publication-title: TKDE
– volume: 36
  start-page: 1134
  year: 2014
  end-page: 1148
  ident: bib0027
  article-title: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation
  publication-title: TPAMI
– start-page: 1
  year: 2016
  end-page: 6
  ident: bib0028
  article-title: Recognizing heterogeneous cross-domain data via generalized joint distribution adaptation
  publication-title: ICME
– start-page: 97
  year: 2015
  end-page: 105
  ident: bib0006
  article-title: Learning transferable features with deep adaptation networks
  publication-title: ICML
– year: 2018
  ident: bib0021
  article-title: Transferable representation learning with deep adaptation networks
  publication-title: TPAMI
– start-page: 402
  year: 2018
  end-page: 410
  ident: bib0014
  article-title: Visual domain adaptation with manifold embedded distribution alignment
  publication-title: ACM MM
– start-page: 1049
  year: 2010
  end-page: 1054
  ident: bib0024
  article-title: Transfer learning on heterogenous feature spaces via spectral transformation
  publication-title: ICDM
– start-page: 3012
  year: 2018
  end-page: 3018
  ident: bib0046
  article-title: Distance metric facilitated transportation between heterogeneous domains
  publication-title: IJCAI
– volume: 28
  start-page: 6103
  year: 2019
  end-page: 6115
  ident: bib0038
  article-title: Locality preserving joint transfer for domain adaptation
  publication-title: TIP
– volume: 26
  start-page: 1076
  year: 2014
  end-page: 1089
  ident: bib0019
  article-title: Adaptation regularization: a general framework for transfer learning
  publication-title: TKDE
– volume: 4
  start-page: 29
  year: 2017
  ident: bib0004
  article-title: A survey on heterogeneous transfer learning
  publication-title: J. Big Data
– start-page: 513
  year: 2007
  end-page: 520
  ident: bib0048
  article-title: A kernel method for the two-sample-problem
  publication-title: NeurIPS
– volume: 3
  year: 2016
  ident: bib0002
  article-title: A survey of transfer learning
  publication-title: J. Big Data
– year: 2018
  ident: bib0022
  article-title: Unsupervised domain adaptation with distribution matching machines
  publication-title: AAAI
– volume: 49
  start-page: 2144
  year: 2019
  end-page: 2155
  ident: bib0040
  article-title: Transfer independently together: A generalized framework for domain adaptation
  publication-title: TYCB
– start-page: 1
  year: 2018
  end-page: 11
  ident: bib0036
  article-title: Heterogeneous domain adaptation through progressive alignment
  publication-title: TNNLS
– year: 2014
  ident: bib0057
  article-title: Decaf: A deep convolutional activation feature for generic visual recognition
  publication-title: ICML
– volume: 109
  start-page: 28
  year: 2014
  end-page: 41
  ident: bib0031
  article-title: Asymmetric and category invariant feature transformations for domain adaptation
  publication-title: IJCV
– start-page: 343
  year: 2016
  end-page: 351
  ident: bib0020
  article-title: Domain separation networks
  publication-title: NeurIPS
– volume: 81
  start-page: 615
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0012
  article-title: Learning domain-shared group-sparse representation for unsupervised domain adaptation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2018.04.027
– year: 2008
  ident: 10.1016/j.patcog.2019.107165_bib0045
– start-page: 1304
  year: 2011
  ident: 10.1016/j.patcog.2019.107165_bib0011
  article-title: Heterogeneous transfer learning for image classification
– start-page: 525
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_bib0016
  article-title: Semi-supervised subspace co-projection for multi-class heterogeneous domain adaptation
– start-page: 1095
  year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0032
  article-title: Heterogeneous domain adaptation for multiple classes
– volume: 3
  issue: 9
  year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0002
  article-title: A survey of transfer learning
  publication-title: J. Big Data
– start-page: 3221
  year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0058
  article-title: Accelerating t-SNE using tree-based algorithms
  publication-title: JMLR
– volume: 75
  start-page: 235
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0008
  article-title: Semi-supervised transfer subspace for domain adaptation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2017.04.011
– start-page: 404
  year: 2006
  ident: 10.1016/j.patcog.2019.107165_bib0056
  article-title: Surf: Speeded up robust features
– start-page: 3252
  year: 2017
  ident: 10.1016/j.patcog.2019.107165_bib0035
  article-title: Learning discriminative correlation subspace for heterogeneous domain adaptation
– start-page: 402
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0014
  article-title: Visual domain adaptation with manifold embedded distribution alignment
– volume: 35
  start-page: 773
  year: 1980
  ident: 10.1016/j.patcog.2019.107165_bib0050
  article-title: Updating Quasi-Newton matrices with limited storage
  publication-title: Math. Comput.
  doi: 10.1090/S0025-5718-1980-0572855-7
– start-page: 265
  year: 2011
  ident: 10.1016/j.patcog.2019.107165_bib0052
  article-title: On optimization methods for deep learning
– volume: 4
  start-page: 29
  issue: 1
  year: 2017
  ident: 10.1016/j.patcog.2019.107165_bib0004
  article-title: A survey on heterogeneous transfer learning
  publication-title: J. Big Data
  doi: 10.1186/s40537-017-0089-0
– volume: 27
  start-page: 5214
  issue: 11
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0023
  article-title: Semi-supervised deep domain adaptation via coupled neural networks
  publication-title: TIP
– year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0022
  article-title: Unsupervised domain adaptation with distribution matching machines
– start-page: 321
  year: 2004
  ident: 10.1016/j.patcog.2019.107165_bib0039
  article-title: Learning with local and global consistency
– start-page: 3012
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0046
  article-title: Distance metric facilitated transportation between heterogeneous domains
– start-page: 5081
  year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0033
  article-title: Learning cross-domain landmarks for heterogeneous domain adaptation
– start-page: 8602
  year: 2019
  ident: 10.1016/j.patcog.2019.107165_bib0043
  article-title: Heterogeneous transfer learning via deep matrix completion with adversarial kernel embedding
– start-page: 343
  year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0020
  article-title: Domain separation networks
– year: 2007
  ident: 10.1016/j.patcog.2019.107165_bib0054
– start-page: 2969
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0047
  article-title: Semi-supervised optimal transport for heterogeneous domain adaptation
– year: 2013
  ident: 10.1016/j.patcog.2019.107165_bib0030
  article-title: Efficient learning of domain-invariant image representations
– start-page: 1155
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_bib0018
  article-title: Transitive transfer learning
– volume: 36
  start-page: 1134
  issue: 6
  year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0027
  article-title: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2013.167
– start-page: 2142
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_bib0010
  article-title: Semi-supervised domain adaptation with subspace learning for visual recognition
– start-page: 35
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_sbref0040
  article-title: Weakly-shared deep transfer networks for heterogeneous-domain knowledge propagation
– volume: 80
  start-page: 109
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0015
  article-title: Adaptive batch normalization for practical domain adaptation
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2018.03.005
– start-page: 1049
  year: 2010
  ident: 10.1016/j.patcog.2019.107165_bib0024
  article-title: Transfer learning on heterogenous feature spaces via spectral transformation
– start-page: 5150
  year: 2017
  ident: 10.1016/j.patcog.2019.107165_bib0009
  article-title: Joint geometrical and statistical alignment for visual domain adaptation
– ident: 10.1016/j.patcog.2019.107165_bib0003
  doi: 10.1007/978-3-319-58347-1_1
– start-page: 1
  year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0028
  article-title: Recognizing heterogeneous cross-domain data via generalized joint distribution adaptation
– year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0057
  article-title: Decaf: A deep convolutional activation feature for generic visual recognition
– volume: 37
  start-page: 54
  issue: 1
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_bib0017
  article-title: Feature space independent semi-supervised domain adaptation via kernel matching
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2014.2343216
– volume: 41
  start-page: 1013
  issue: 4
  year: 2019
  ident: 10.1016/j.patcog.2019.107165_bib0044
  article-title: Transferring knowledge fragments for learning distance metric from a heterogeneous domain
  publication-title: TPAMI
  doi: 10.1109/TPAMI.2018.2824309
– start-page: 2842
  year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0034
  article-title: Heterogeneous domain adaptation with label and structure consistency
– volume: 49
  start-page: 2144
  issue: 6
  year: 2019
  ident: 10.1016/j.patcog.2019.107165_bib0040
  article-title: Transfer independently together: A generalized framework for domain adaptation
  publication-title: TYCB
– start-page: 2604
  year: 2017
  ident: 10.1016/j.patcog.2019.107165_bib0013
  article-title: Distant domain transfer learning
– volume: 45
  start-page: 503
  issue: 1
  year: 1989
  ident: 10.1016/j.patcog.2019.107165_bib0051
  article-title: On the limited memory bfgs method for large scale optimization
  publication-title: Math. Program.
  doi: 10.1007/BF01589116
– start-page: 97
  year: 2015
  ident: 10.1016/j.patcog.2019.107165_bib0006
  article-title: Learning transferable features with deep adaptation networks
– start-page: 1
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0036
  article-title: Heterogeneous domain adaptation through progressive alignment
  publication-title: TNNLS
– volume: 28
  start-page: 6103
  issue: 12
  year: 2019
  ident: 10.1016/j.patcog.2019.107165_bib0038
  article-title: Locality preserving joint transfer for domain adaptation
  publication-title: TIP
– start-page: 213
  year: 2010
  ident: 10.1016/j.patcog.2019.107165_bib0053
  article-title: Adapting visual category models to new domains
– start-page: 28
  year: 2009
  ident: 10.1016/j.patcog.2019.107165_bib0055
  article-title: Learning from multiple partially observed views - an application to multilingual text categorization
– start-page: 1785
  year: 2011
  ident: 10.1016/j.patcog.2019.107165_bib0029
  article-title: What you saw is not what you get: domain adaptation using asymmetric kernel transforms
– start-page: 2200
  year: 2013
  ident: 10.1016/j.patcog.2019.107165_bib0005
  article-title: Transfer feature learning with joint distribution adaptation
– volume: 26
  start-page: 1076
  issue: 5
  year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0019
  article-title: Adaptation regularization: a general framework for transfer learning
  publication-title: TKDE
– volume: 22
  start-page: 1345
  issue: 10
  year: 2010
  ident: 10.1016/j.patcog.2019.107165_bib0001
  article-title: A survey on transfer learning
  publication-title: TKDE
– volume: 109
  start-page: 28
  issue: 1
  year: 2014
  ident: 10.1016/j.patcog.2019.107165_bib0031
  article-title: Asymmetric and category invariant feature transformations for domain adaptation
  publication-title: IJCV
  doi: 10.1007/s11263-014-0719-3
– year: 1998
  ident: 10.1016/j.patcog.2019.107165_bib0049
– year: 2018
  ident: 10.1016/j.patcog.2019.107165_sbref0020
  article-title: Transferable representation learning with deep adaptation networks
  publication-title: TPAMI
– start-page: 513
  year: 2007
  ident: 10.1016/j.patcog.2019.107165_bib0048
  article-title: A kernel method for the two-sample-problem
– start-page: 1541
  year: 2011
  ident: 10.1016/j.patcog.2019.107165_bib0025
  article-title: Heterogeneous domain adaptation using manifold alignment
– start-page: 2208
  year: 2017
  ident: 10.1016/j.patcog.2019.107165_bib0007
  article-title: Deep transfer learning with joint adaptation networks
– volume: 106
  start-page: 13
  year: 2018
  ident: 10.1016/j.patcog.2019.107165_bib0037
  article-title: A discriminative feature mapping approach to heterogeneous domain adaptation
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2018.02.011
– start-page: 711
  year: 2012
  ident: 10.1016/j.patcog.2019.107165_bib0026
  article-title: Learning with augmented features for heterogeneous domain adaptation
– year: 2016
  ident: 10.1016/j.patcog.2019.107165_bib0042
  article-title: Transfer neural trees for heterogeneous domain adaptation
SSID ssj0017142
Score 2.4900198
Snippet •We design a discriminative embedding constraint for the heterogeneous domain adaptation problem, which enhances the discriminative power of the common...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 107165
SubjectTerms Classifier adaptation
Discriminative embedding
Distribution alignment
Heterogeneous domain adaptation
Subspace learning
Title Discriminative distribution alignment: A unified framework for heterogeneous domain adaptation
URI https://dx.doi.org/10.1016/j.patcog.2019.107165
Volume 101
WOSCitedRecordID wos000525824600002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-5142
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017142
  issn: 0031-3203
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT-MwELZWhQMXYHmI58oHbsgoqZPa5lYtrBYOCGlBai9ESWxDESQVNIifv-PYcVqBeElcosqN3crzafx5_HkGob2MAmwYC4lkjJFIqoBkQLuJ0FkvplEes9QWm2BnZ3wwEOfuoP2xLifAioI_P4vxt5oa2sDY5ursJ8ztB4UG-AxGhyeYHZ4fMvzRyHgCo3CpVUHSZMZ1Ra32gXRfFz4euF8VI20oqG4UWrXo8MYoZEoYXxl5rCzv0xH0lOl46tTe0dnzOjunuRHjZEjtof4wrYOww6qFnw9ODyuvA6rFBINqkpZt9Na-Utw3q6oLSnSDVgJoI2XNbZlWmlR7XxoS2g2sQ1PW4XJGCZC2WY9sh3rh3W2g4fZgDKtUeW10eQIaYccXt6uZ1xj-s2kpzS0tc_pr4jpzXRYL3kFz_ZPjwak_bGJhZJPKu7_X3LCsZYAvf-t1BjPFSi6W0aLbTuC-hcFP9EMVK2ipKdWBnedeRVezqMDTqMAeFYe4jx0msMcEBkzgGUxgiwncYmINXf45vvj9l7jSGiSHPeKEKNhnp2FGVVcGAhhbL4tTChstpoHw6jCWwPJlJDLgc1orc1oNk6Riqky1gSiUdB11irJQGwgHOudChkFPcA7fRJzSQDGe5VRoqrjaRLSZriR3eedN-ZO7pBEY3iZ2khMzyYmd5E1EfK-xzbvyzvussUTiuKPlhAmA582eW1_uuY0WWuzvoM7koVK7aD5_moweH345lP0Han2WSA
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Discriminative+distribution+alignment%3A+A+unified+framework+for+heterogeneous+domain+adaptation&rft.jtitle=Pattern+recognition&rft.au=Yao%2C+Yuan&rft.au=Zhang%2C+Yu&rft.au=Li%2C+Xutao&rft.au=Ye%2C+Yunming&rft.date=2020-05-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.eissn=1873-5142&rft.volume=101&rft_id=info:doi/10.1016%2Fj.patcog.2019.107165&rft.externalDocID=S0031320319304650
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon