Self-supervised autoencoders for clustering and classification

Clustering techniques aim at finding meaningful groups of data samples which exhibit similarity with regards to a set of characteristics, typically measured in terms of pairwise distances. Due to the so-called curse of dimensionality, i.e., the observation that high-dimensional spaces are unsuited f...

Full description

Saved in:
Bibliographic Details
Published in:Evolving systems Vol. 11; no. 3; pp. 453 - 466
Main Authors: Nousi, Paraskevi, Tefas, Anastasios
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2020
Subjects:
ISSN:1868-6478, 1868-6486
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Clustering techniques aim at finding meaningful groups of data samples which exhibit similarity with regards to a set of characteristics, typically measured in terms of pairwise distances. Due to the so-called curse of dimensionality, i.e., the observation that high-dimensional spaces are unsuited for measuring distances, distance-based clustering techniques such as the classic k -means algorithm fail to uncover meaningful clusters in high-dimensional spaces. Thus, dimensionality reduction techniques can be used to greatly improve the performance of such clustering methods. In this work, we study Autoencoders as Deep Learning tools for dimensionality reduction, and combine them with k -means clustering to learn low-dimensional representations which improve the clustering performance by enhancing intra-cluster relationships and suppressing inter-cluster ones, in a self-supervised manner. In the supervised paradigm, distance-based classifiers may also greatly benefit from robust dimensionality reduction techniques. The proposed method is evaluated via multiple experiments on datasets of handwritten digits, various objects and faces, and is shown to improve external cluster quality measuring criteria. A fully supervised counterpart is also evaluated on two face recognition datasets, and is shown to improve the performance of various lightweight classifiers, allowing their use in real-time applications on devices with limited computational resources, such as Unmanned Aerial Vehicles (UAVs).
AbstractList Clustering techniques aim at finding meaningful groups of data samples which exhibit similarity with regards to a set of characteristics, typically measured in terms of pairwise distances. Due to the so-called curse of dimensionality, i.e., the observation that high-dimensional spaces are unsuited for measuring distances, distance-based clustering techniques such as the classic k -means algorithm fail to uncover meaningful clusters in high-dimensional spaces. Thus, dimensionality reduction techniques can be used to greatly improve the performance of such clustering methods. In this work, we study Autoencoders as Deep Learning tools for dimensionality reduction, and combine them with k -means clustering to learn low-dimensional representations which improve the clustering performance by enhancing intra-cluster relationships and suppressing inter-cluster ones, in a self-supervised manner. In the supervised paradigm, distance-based classifiers may also greatly benefit from robust dimensionality reduction techniques. The proposed method is evaluated via multiple experiments on datasets of handwritten digits, various objects and faces, and is shown to improve external cluster quality measuring criteria. A fully supervised counterpart is also evaluated on two face recognition datasets, and is shown to improve the performance of various lightweight classifiers, allowing their use in real-time applications on devices with limited computational resources, such as Unmanned Aerial Vehicles (UAVs).
Author Tefas, Anastasios
Nousi, Paraskevi
Author_xml – sequence: 1
  givenname: Paraskevi
  orcidid: 0000-0002-3087-3174
  surname: Nousi
  fullname: Nousi, Paraskevi
  email: paranous@csd.auth.gr
  organization: Department of Informatics, Aristotle University of Thessaloniki
– sequence: 2
  givenname: Anastasios
  surname: Tefas
  fullname: Tefas, Anastasios
  organization: Department of Informatics, Aristotle University of Thessaloniki
BookMark eNp9kMFKAzEQhoNUsNY-gLd9gegkm91kL4IUtULBg3oO2exEUtakJLtC396tFQ8eepqZw_cz_3dJZiEGJOSawQ0DkLeZ8aoECkzRhpcV3Z-ROVO1orVQ9exvl-qCLHPeAgBnAkDIObl7xd7RPO4wffmMXWHGIWKwscOUCxdTYfsxD5h8-ChM6KbT5Oydt2bwMVyRc2f6jMvfuSDvjw9vqzXdvDw9r-431HKlBopWdVDy1oJC5gRTkvFWdlC3FWcNShCiaaGRAsF2tqmtUo1jwjYM28qVdbkg8phrU8w5odPWDz8fDMn4XjPQBxP6aEJPJvTBhN5PJPtH7pL_NGl_kuFHJu8OvTHpbRxTmAqegL4Bb9Vzsw
CitedBy_id crossref_primary_10_1109_ACCESS_2020_3017082
crossref_primary_10_1109_TNNLS_2022_3190448
crossref_primary_10_1109_TNNLS_2022_3195780
crossref_primary_10_1007_s00521_018_3712_x
crossref_primary_10_1007_s11831_025_10260_5
crossref_primary_10_1016_j_imavis_2024_105258
crossref_primary_10_1016_j_ijepes_2024_109861
crossref_primary_10_1109_ACCESS_2024_3465497
crossref_primary_10_1007_s42979_022_01428_y
crossref_primary_10_1109_JSYST_2025_3532508
crossref_primary_10_1007_s10489_020_01701_8
crossref_primary_10_1016_j_eswa_2024_126165
Cites_doi 10.1111/j.1469-1809.1936.tb02137.x
10.1109/CVPR.2016.556
10.1016/S0031-3203(02)00060-2
10.1109/NNSP.1999.788121
10.1109/TIT.2014.2375327
10.1109/TNNLS.2014.2329240
10.1609/aaai.v28i1.8916
10.1145/1015330.1015332
10.1007/3-540-44503-X_27
10.1016/j.neucom.2017.05.042
10.1016/j.patrec.2009.09.011
10.1145/1273496.1273562
10.1109/5.726791
10.1007/978-3-642-41822-8_15
10.1109/CVPR.2014.227
10.1016/j.asoc.2015.05.026
10.1145/1014052.1014118
10.1023/A:1009769707641
10.1007/978-3-319-14998-1_17
10.21236/ADA164453
10.1109/TIP.2014.2348868
10.1109/TPAMI.2005.92
10.1016/j.eswa.2012.07.021
10.1016/0098-3004(84)90020-7
10.1145/1015330.1015408
10.14569/IJACSA.2013.040406
10.1145/1273496.1273523
10.1109/CVPR.2015.7298682
10.1007/978-3-319-65172-9_18
10.1002/nav.3800020109
10.1016/j.patrec.2004.04.007
10.1109/ICPR.2014.272
10.1016/j.patcog.2015.02.020
10.1109/34.598228
10.1145/1390156.1390294
ContentType Journal Article
Copyright Springer-Verlag GmbH Germany, part of Springer Nature 2018
Copyright_xml – notice: Springer-Verlag GmbH Germany, part of Springer Nature 2018
DBID AAYXX
CITATION
DOI 10.1007/s12530-018-9235-y
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1868-6486
EndPage 466
ExternalDocumentID 10_1007_s12530_018_9235_y
GroupedDBID -EM
06D
0R~
0VY
1N0
203
29~
2JY
2VQ
30V
4.4
406
408
409
40D
96X
AAAVM
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATLR
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
AAZMS
ABAKF
ABBXA
ABDZT
ABECU
ABFTV
ABHQN
ABJNI
ABJOX
ABKCH
ABMQK
ABQBU
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACKNC
ACMLO
ACOKC
ACPIV
ACZOJ
ADHHG
ADHIR
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFQL
AEGNC
AEJHL
AEJRE
AEMSY
AEOHA
AEPYU
AESKC
AETCA
AEVLU
AEXYK
AFBBN
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
AKLTO
ALFXC
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AMXSW
AMYLF
AMYQR
ANMIH
ARAPS
AUKKA
AXYYD
AYJHY
BENPR
BGLVJ
BGNMA
CCPQU
CSCUP
DNIVK
DPUIP
EBLON
EBS
EIOEI
EJD
ESBYG
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FYJPI
GGCAI
GGRSB
GJIRD
GQ6
GQ7
GQ8
H13
HCIFZ
HF~
HG6
HMJXF
HQYDN
HRMNR
HZ~
I0C
IKXTQ
IWAJR
IXD
IZIGR
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K7-
KOV
LLZTM
M4Y
NPVJJ
NQJWS
NU0
O9-
O93
O9J
P9P
PT4
QOS
R89
R9I
RLLFE
ROL
RSV
S1Z
S27
S3B
SEG
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
T13
TSG
U2A
UG4
UOJIU
UTJUX
UZXMN
VFIZW
W48
WK8
Z45
Z83
Z88
ZMTXR
~A9
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AHPBZ
AHWEU
AIXLP
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
ID FETCH-LOGICAL-c288t-ec8d032bc08e1f418712b7d06b5219e70449b0974e0cdc96c889f14c91eb5f363
IEDL.DBID RSV
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000563132800008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1868-6478
IngestDate Sat Nov 29 07:49:35 EST 2025
Tue Nov 18 22:35:34 EST 2025
Fri Feb 21 02:34:59 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 3
Keywords Dimensionality reduction
Deep learning
Clustering
Autoencoders
Classification
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c288t-ec8d032bc08e1f418712b7d06b5219e70449b0974e0cdc96c889f14c91eb5f363
ORCID 0000-0002-3087-3174
PageCount 14
ParticipantIDs crossref_citationtrail_10_1007_s12530_018_9235_y
crossref_primary_10_1007_s12530_018_9235_y
springer_journals_10_1007_s12530_018_9235_y
PublicationCentury 2000
PublicationDate 20200900
2020-09-00
PublicationDateYYYYMMDD 2020-09-01
PublicationDate_xml – month: 9
  year: 2020
  text: 20200900
PublicationDecade 2020
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
PublicationSubtitle An Interdisciplinary Journal for Advanced Science and Technology
PublicationTitle Evolving systems
PublicationTitleAbbrev Evolving Systems
PublicationYear 2020
Publisher Springer Berlin Heidelberg
Publisher_xml – name: Springer Berlin Heidelberg
References LeCunYBottouLBengioYHaffnerPGradient-based learning applied to document recognitionProc IEEE199886112278232410.1109/5.726791
Dhillon IS, Guan Y, Kulis B (2004) Kernel k-means: spectral clustering and normalized cuts. In: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 551–556
Wang J, Wang J, Ke Q, Zeng G, Li S (2015) Fast approximate k-means via cluster closures. In: Multimedia Data Mining and Analytics. Springer, pp 373–395
BelhumeurPNHespanhaJPKriegmanDJEigenfaces vs. fisherfaces: recognition using class specific linear projectionIEEE Trans Pattern Anal Mach Intell199719771172010.1109/34.598228
Zhang T (2004) Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the twenty-first international conference on Machine learning. ACM, p 116
Aggarwal CC, Hinneburg A, Keim DA (2001) On the surprising behavior of distance metrics in high dimensional spaces. In: ICDT, vol 1. Springer, pp 420–434
Mika S, Ratsch G, Weston J, Scholkopf B, Mullers KR (1999) Fisher discriminant analysis with kernels. In: Neural Networks for Signal Processing IX, 1999. Proceedings of the 1999 IEEE Signal Processing Society Workshop., pp 41–48. IEEE
HuangZExtensions to the k-means algorithm for clustering large data sets with categorical valuesData Min Knowl Disc19982328330410.1023/A:1009769707641
Jolliffe I (2002) Principal component analysis. Wiley Online Library
Ding C, He X (2004) K-means clustering via principal component analysis. In: Proceedings of the twenty-first international conference on Machine learning. ACM, p 29
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 815–823
BhuiyanAALiuCHOn face recognition using gabor filtersWorld Acad Sci Eng Technol2007285156
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Huang P, Huang Y, Wang W, Wang L (2014) Deep embedding network for clustering. In: 2014 22nd International Conference on Pattern Recognition (ICPR). IEEE, pp 1532–1537
CelebiMEKingraviHAVelaPAA comparative study of efficient initialization methods for the k-means clustering algorithmExpert Syst Appl201340120021010.1016/j.eswa.2012.07.021
Passalis N, Tefas A (2017) Dimensionality reduction using similarity-induced embeddings. IEEE Trans Neural Netw Learn Syst
Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: Proceedings of the 24th international conference on Machine learning. ACM, pp 209–216
Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Tech. rep, DTIC Document
Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp 478–487
BouzasDArvanitopoulosNTefasAGraph embedded nonparametric mutual information for supervised dimensionality reductionIEEE Trans Neural Netw Learn Syst2015265951963345425510.1109/TNNLS.2014.2329240
Guo G, Li SZ, Chan K (2000) Face recognition by support vector machines. In: Fourth IEEE International Conference on Automatic Face and Gesture Recognition, 2000. Proceedings, pp 196–201. IEEE
Nene SA, Nayar SK, Murase H et al (1996) Columbia object image library (coil-20)
Dehghan A, Ortiz EG, Villegas R, Shah M (2014) Who do i look like? Determining parent-offspring resemblance via gated autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1757–1764
LikasAVlassisNVerbeekJJThe global k-means clustering algorithmPattern Recogn200336245146110.1016/S0031-3203(02)00060-2
SrivastavaNHintonGEKrizhevskyASutskeverISalakhutdinovRDropout: a simple way to prevent neural networks from overfittingJ Mach Learn Res20141511929195832315921318.68153
KhanSSAhmadACluster center initialization algorithm for k-means clusteringPattern Recogn Lett200425111293130210.1016/j.patrec.2004.04.007
Xing EP, Jordan MI, Russell SJ, Ng AY (2003) Distance metric learning with application to clustering with side-information. In: Advances in neural information processing systems, pp 521–528
JainAKData clustering: 50 years beyond k-meansPattern Recogn Lett201031865166610.1016/j.patrec.2009.09.011
KuhnHWThe Hungarian method for the assignment problemNRL195521–283977551010.1002/nav.3800020109
Nousi P, Tefas A (2017) Discriminatively trained autoencoders for fast and accurate face recognition. In: International Conference on Engineering Applications of Neural Networks. Springer, pp 205–215
TsapanosNTefasANikolaidisNPitasIA distributed framework for trimmed kernel k-means clusteringPattern Recogn20154882685269810.1016/j.patcog.2015.02.020
Le QV (2013) Building high-level features using large scale unsupervised learning. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 8595–8598
NikitidisSTefasAPitasIMaximum margin projection subspace learning for visual data analysisIEEE Trans Image Process2014231044134425330009010.1109/TIP.2014.2348868
FisherRAThe use of multiple measurements in taxonomic problemsAnn Eugen19367217918810.1111/j.1469-1809.1936.tb02137.x
Ghosh S, Dubey SK (2013) Comparative analysis of k-means and fuzzy c-means algorithms. Int J Adv Comput Sci Appl 4(4)
Yang J, Parikh D, Batra D (2016) Joint unsupervised learning of deep representations and image clusters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5147–5156
Passalis N, Tefas A (2016) Information clustering using manifold-based optimization of the bag-of-features representation. IEEE Trans Cybern
BoutsidisCZouziasAMahoneyMWDrineasPRandomized dimensionality reduction for k\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ k $$\end{document}-means clusteringIEEE Trans Inf Theory201561210451062333276410.1109/TIT.2014.2375327
Song C, Liu F, Huang Y, Wang L, Tan T (2013) Auto-encoder based data clustering. In: Iberoamerican Congress on Pattern Recognition. Springer, pp 117–124
Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on Machine learning. ACM, pp 1096–1103
ChrysouliCTefasASpectral clustering and semi-supervised learning using evolving similarity graphsAppl Soft Comput20153462563710.1016/j.asoc.2015.05.026
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
Strehl A, Ghosh J (2002) Cluster ensembles—a knowledge reuse framework for combining multiple partitions. J Mach Learn Res 3:583–617
Ding C, Li T (2007) Adaptive dimension reduction using discriminant analysis and k-means clustering. In: Proceedings of the 24th international conference on Machine learning. ACM, pp 521–528
Nousi P, Tefas A (2017) Deep learning algorithms for discriminant autoencoding. Neurocomputing
Rolfe JT, LeCun Y (2013) Discriminative recurrent sparse auto-encoders. arXiv preprint arXiv:1301.3775
MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1. Oakland, CA, USA, pp 281–297
LeeKCHoJKriegmanDJAcquiring linear subspaces for face recognition under variable lightingIEEE Trans Pattern Anal Mach Intell200527568469810.1109/TPAMI.2005.92
Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. Society for Industrial and Applied Mathematics, pp 1027–1035
BezdekJCEhrlichRFullWFcm: the fuzzy c-means clustering algorithmComput Geosci1984102–319120310.1016/0098-3004(84)90020-7
Beyer K, Goldstein J, Ramakrishnan R, Shaft U (1999) When is nearest neighbor meaningful? In: International conference on database theory. Springer, pp 217–235
Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of the Second IEEE Workshop on Applications of Computer Vision. IEEE, pp 138–142
Tian F, Gao B, Cui Q, Chen E, Liu TY (2014) Learning deep representations for graph clustering. In: AAAI, pp 1293–1299
AA Bhuiyan (9235_CR6) 2007; 28
AK Jain (9235_CR22) 2010; 31
Y LeCun (9235_CR29) 1998; 86
9235_CR20
9235_CR23
9235_CR25
9235_CR26
9235_CR4
9235_CR28
HW Kuhn (9235_CR27) 1955; 2
N Tsapanos (9235_CR48) 2015; 48
N Srivastava (9235_CR45) 2014; 15
Z Huang (9235_CR21) 1998; 2
9235_CR1
9235_CR2
PN Belhumeur (9235_CR3) 1997; 19
9235_CR50
9235_CR51
C Boutsidis (9235_CR7) 2015; 61
ME Celebi (9235_CR9) 2013; 40
9235_CR52
9235_CR53
9235_CR54
9235_CR11
9235_CR12
9235_CR13
9235_CR14
9235_CR15
9235_CR17
9235_CR18
9235_CR19
C Chrysouli (9235_CR10) 2015; 34
RA Fisher (9235_CR16) 1936; 7
9235_CR40
9235_CR41
9235_CR42
9235_CR43
9235_CR44
9235_CR46
9235_CR47
9235_CR49
JC Bezdek (9235_CR5) 1984; 10
9235_CR32
D Bouzas (9235_CR8) 2015; 26
9235_CR33
SS Khan (9235_CR24) 2004; 25
9235_CR34
9235_CR36
9235_CR37
KC Lee (9235_CR30) 2005; 27
9235_CR38
9235_CR39
A Likas (9235_CR31) 2003; 36
S Nikitidis (9235_CR35) 2014; 23
References_xml – reference: ChrysouliCTefasASpectral clustering and semi-supervised learning using evolving similarity graphsAppl Soft Comput20153462563710.1016/j.asoc.2015.05.026
– reference: Ghosh S, Dubey SK (2013) Comparative analysis of k-means and fuzzy c-means algorithms. Int J Adv Comput Sci Appl 4(4)
– reference: Passalis N, Tefas A (2016) Information clustering using manifold-based optimization of the bag-of-features representation. IEEE Trans Cybern
– reference: Rolfe JT, LeCun Y (2013) Discriminative recurrent sparse auto-encoders. arXiv preprint arXiv:1301.3775
– reference: Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
– reference: Passalis N, Tefas A (2017) Dimensionality reduction using similarity-induced embeddings. IEEE Trans Neural Netw Learn Syst
– reference: Song C, Liu F, Huang Y, Wang L, Tan T (2013) Auto-encoder based data clustering. In: Iberoamerican Congress on Pattern Recognition. Springer, pp 117–124
– reference: Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on Machine learning. ACM, pp 1096–1103
– reference: KuhnHWThe Hungarian method for the assignment problemNRL195521–283977551010.1002/nav.3800020109
– reference: Tian F, Gao B, Cui Q, Chen E, Liu TY (2014) Learning deep representations for graph clustering. In: AAAI, pp 1293–1299
– reference: Wang J, Wang J, Ke Q, Zeng G, Li S (2015) Fast approximate k-means via cluster closures. In: Multimedia Data Mining and Analytics. Springer, pp 373–395
– reference: HuangZExtensions to the k-means algorithm for clustering large data sets with categorical valuesData Min Knowl Disc19982328330410.1023/A:1009769707641
– reference: FisherRAThe use of multiple measurements in taxonomic problemsAnn Eugen19367217918810.1111/j.1469-1809.1936.tb02137.x
– reference: Xing EP, Jordan MI, Russell SJ, Ng AY (2003) Distance metric learning with application to clustering with side-information. In: Advances in neural information processing systems, pp 521–528
– reference: SrivastavaNHintonGEKrizhevskyASutskeverISalakhutdinovRDropout: a simple way to prevent neural networks from overfittingJ Mach Learn Res20141511929195832315921318.68153
– reference: Le QV (2013) Building high-level features using large scale unsupervised learning. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 8595–8598
– reference: Nousi P, Tefas A (2017) Deep learning algorithms for discriminant autoencoding. Neurocomputing
– reference: MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1. Oakland, CA, USA, pp 281–297
– reference: Zhang T (2004) Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the twenty-first international conference on Machine learning. ACM, p 116
– reference: BoutsidisCZouziasAMahoneyMWDrineasPRandomized dimensionality reduction for k\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$ k $$\end{document}-means clusteringIEEE Trans Inf Theory201561210451062333276410.1109/TIT.2014.2375327
– reference: LikasAVlassisNVerbeekJJThe global k-means clustering algorithmPattern Recogn200336245146110.1016/S0031-3203(02)00060-2
– reference: Yang J, Parikh D, Batra D (2016) Joint unsupervised learning of deep representations and image clusters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5147–5156
– reference: Dhillon IS, Guan Y, Kulis B (2004) Kernel k-means: spectral clustering and normalized cuts. In: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 551–556
– reference: Davis JV, Kulis B, Jain P, Sra S, Dhillon IS (2007) Information-theoretic metric learning. In: Proceedings of the 24th international conference on Machine learning. ACM, pp 209–216
– reference: KhanSSAhmadACluster center initialization algorithm for k-means clusteringPattern Recogn Lett200425111293130210.1016/j.patrec.2004.04.007
– reference: Dehghan A, Ortiz EG, Villegas R, Shah M (2014) Who do i look like? Determining parent-offspring resemblance via gated autoencoders. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1757–1764
– reference: Ding C, Li T (2007) Adaptive dimension reduction using discriminant analysis and k-means clustering. In: Proceedings of the 24th international conference on Machine learning. ACM, pp 521–528
– reference: Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105
– reference: Arthur D, Vassilvitskii S (2007) k-means++: the advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms. Society for Industrial and Applied Mathematics, pp 1027–1035
– reference: BelhumeurPNHespanhaJPKriegmanDJEigenfaces vs. fisherfaces: recognition using class specific linear projectionIEEE Trans Pattern Anal Mach Intell199719771172010.1109/34.598228
– reference: Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
– reference: Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 815–823
– reference: BhuiyanAALiuCHOn face recognition using gabor filtersWorld Acad Sci Eng Technol2007285156
– reference: BouzasDArvanitopoulosNTefasAGraph embedded nonparametric mutual information for supervised dimensionality reductionIEEE Trans Neural Netw Learn Syst2015265951963345425510.1109/TNNLS.2014.2329240
– reference: JainAKData clustering: 50 years beyond k-meansPattern Recogn Lett201031865166610.1016/j.patrec.2009.09.011
– reference: Strehl A, Ghosh J (2002) Cluster ensembles—a knowledge reuse framework for combining multiple partitions. J Mach Learn Res 3:583–617
– reference: Jolliffe I (2002) Principal component analysis. Wiley Online Library
– reference: Guo G, Li SZ, Chan K (2000) Face recognition by support vector machines. In: Fourth IEEE International Conference on Automatic Face and Gesture Recognition, 2000. Proceedings, pp 196–201. IEEE
– reference: Ding C, He X (2004) K-means clustering via principal component analysis. In: Proceedings of the twenty-first international conference on Machine learning. ACM, p 29
– reference: Nene SA, Nayar SK, Murase H et al (1996) Columbia object image library (coil-20)
– reference: LeCunYBottouLBengioYHaffnerPGradient-based learning applied to document recognitionProc IEEE199886112278232410.1109/5.726791
– reference: Huang P, Huang Y, Wang W, Wang L (2014) Deep embedding network for clustering. In: 2014 22nd International Conference on Pattern Recognition (ICPR). IEEE, pp 1532–1537
– reference: Beyer K, Goldstein J, Ramakrishnan R, Shaft U (1999) When is nearest neighbor meaningful? In: International conference on database theory. Springer, pp 217–235
– reference: BezdekJCEhrlichRFullWFcm: the fuzzy c-means clustering algorithmComput Geosci1984102–319120310.1016/0098-3004(84)90020-7
– reference: Xie J, Girshick R, Farhadi A (2016) Unsupervised deep embedding for clustering analysis. In: International Conference on Machine Learning, pp 478–487
– reference: Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of the Second IEEE Workshop on Applications of Computer Vision. IEEE, pp 138–142
– reference: TsapanosNTefasANikolaidisNPitasIA distributed framework for trimmed kernel k-means clusteringPattern Recogn20154882685269810.1016/j.patcog.2015.02.020
– reference: Nousi P, Tefas A (2017) Discriminatively trained autoencoders for fast and accurate face recognition. In: International Conference on Engineering Applications of Neural Networks. Springer, pp 205–215
– reference: LeeKCHoJKriegmanDJAcquiring linear subspaces for face recognition under variable lightingIEEE Trans Pattern Anal Mach Intell200527568469810.1109/TPAMI.2005.92
– reference: NikitidisSTefasAPitasIMaximum margin projection subspace learning for visual data analysisIEEE Trans Image Process2014231044134425330009010.1109/TIP.2014.2348868
– reference: Aggarwal CC, Hinneburg A, Keim DA (2001) On the surprising behavior of distance metrics in high dimensional spaces. In: ICDT, vol 1. Springer, pp 420–434
– reference: CelebiMEKingraviHAVelaPAA comparative study of efficient initialization methods for the k-means clustering algorithmExpert Syst Appl201340120021010.1016/j.eswa.2012.07.021
– reference: Mika S, Ratsch G, Weston J, Scholkopf B, Mullers KR (1999) Fisher discriminant analysis with kernels. In: Neural Networks for Signal Processing IX, 1999. Proceedings of the 1999 IEEE Signal Processing Society Workshop., pp 41–48. IEEE
– reference: Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Tech. rep, DTIC Document
– ident: 9235_CR2
– volume: 7
  start-page: 179
  issue: 2
  year: 1936
  ident: 9235_CR16
  publication-title: Ann Eugen
  doi: 10.1111/j.1469-1809.1936.tb02137.x
– ident: 9235_CR53
  doi: 10.1109/CVPR.2016.556
– volume: 36
  start-page: 451
  issue: 2
  year: 2003
  ident: 9235_CR31
  publication-title: Pattern Recogn
  doi: 10.1016/S0031-3203(02)00060-2
– ident: 9235_CR33
  doi: 10.1109/NNSP.1999.788121
– volume: 61
  start-page: 1045
  issue: 2
  year: 2015
  ident: 9235_CR7
  publication-title: IEEE Trans Inf Theory
  doi: 10.1109/TIT.2014.2375327
– volume: 26
  start-page: 951
  issue: 5
  year: 2015
  ident: 9235_CR8
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2329240
– ident: 9235_CR47
  doi: 10.1609/aaai.v28i1.8916
– ident: 9235_CR51
– ident: 9235_CR32
– ident: 9235_CR39
– ident: 9235_CR54
  doi: 10.1145/1015330.1015332
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: 9235_CR45
  publication-title: J Mach Learn Res
– ident: 9235_CR42
– ident: 9235_CR1
  doi: 10.1007/3-540-44503-X_27
– ident: 9235_CR25
– ident: 9235_CR46
– ident: 9235_CR23
– ident: 9235_CR36
  doi: 10.1016/j.neucom.2017.05.042
– ident: 9235_CR19
– volume: 31
  start-page: 651
  issue: 8
  year: 2010
  ident: 9235_CR22
  publication-title: Pattern Recogn Lett
  doi: 10.1016/j.patrec.2009.09.011
– ident: 9235_CR15
  doi: 10.1145/1273496.1273562
– volume: 86
  start-page: 2278
  issue: 11
  year: 1998
  ident: 9235_CR29
  publication-title: Proc IEEE
  doi: 10.1109/5.726791
– ident: 9235_CR44
  doi: 10.1007/978-3-642-41822-8_15
– ident: 9235_CR12
  doi: 10.1109/CVPR.2014.227
– volume: 34
  start-page: 625
  year: 2015
  ident: 9235_CR10
  publication-title: Appl Soft Comput
  doi: 10.1016/j.asoc.2015.05.026
– volume: 28
  start-page: 51
  year: 2007
  ident: 9235_CR6
  publication-title: World Acad Sci Eng Technol
– ident: 9235_CR26
– ident: 9235_CR13
  doi: 10.1145/1014052.1014118
– volume: 2
  start-page: 283
  issue: 3
  year: 1998
  ident: 9235_CR21
  publication-title: Data Min Knowl Disc
  doi: 10.1023/A:1009769707641
– ident: 9235_CR50
  doi: 10.1007/978-3-319-14998-1_17
– ident: 9235_CR4
– ident: 9235_CR41
  doi: 10.21236/ADA164453
– volume: 23
  start-page: 4413
  issue: 10
  year: 2014
  ident: 9235_CR35
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2014.2348868
– volume: 27
  start-page: 684
  issue: 5
  year: 2005
  ident: 9235_CR30
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/TPAMI.2005.92
– volume: 40
  start-page: 200
  issue: 1
  year: 2013
  ident: 9235_CR9
  publication-title: Expert Syst Appl
  doi: 10.1016/j.eswa.2012.07.021
– ident: 9235_CR18
– ident: 9235_CR34
– volume: 10
  start-page: 191
  issue: 2–3
  year: 1984
  ident: 9235_CR5
  publication-title: Comput Geosci
  doi: 10.1016/0098-3004(84)90020-7
– ident: 9235_CR14
  doi: 10.1145/1015330.1015408
– ident: 9235_CR40
– ident: 9235_CR17
  doi: 10.14569/IJACSA.2013.040406
– ident: 9235_CR11
  doi: 10.1145/1273496.1273523
– ident: 9235_CR43
  doi: 10.1109/CVPR.2015.7298682
– ident: 9235_CR37
  doi: 10.1007/978-3-319-65172-9_18
– volume: 2
  start-page: 83
  issue: 1–2
  year: 1955
  ident: 9235_CR27
  publication-title: NRL
  doi: 10.1002/nav.3800020109
– volume: 25
  start-page: 1293
  issue: 11
  year: 2004
  ident: 9235_CR24
  publication-title: Pattern Recogn Lett
  doi: 10.1016/j.patrec.2004.04.007
– ident: 9235_CR38
– ident: 9235_CR52
– ident: 9235_CR20
  doi: 10.1109/ICPR.2014.272
– volume: 48
  start-page: 2685
  issue: 8
  year: 2015
  ident: 9235_CR48
  publication-title: Pattern Recogn
  doi: 10.1016/j.patcog.2015.02.020
– volume: 19
  start-page: 711
  issue: 7
  year: 1997
  ident: 9235_CR3
  publication-title: IEEE Trans Pattern Anal Mach Intell
  doi: 10.1109/34.598228
– ident: 9235_CR49
  doi: 10.1145/1390156.1390294
– ident: 9235_CR28
SSID ssj0002140047
ssib031263332
Score 2.2607331
Snippet Clustering techniques aim at finding meaningful groups of data samples which exhibit similarity with regards to a set of characteristics, typically measured in...
SourceID crossref
springer
SourceType Enrichment Source
Index Database
Publisher
StartPage 453
SubjectTerms Artificial Intelligence
Complex Systems
Complexity
Engineering
Original Paper
Title Self-supervised autoencoders for clustering and classification
URI https://link.springer.com/article/10.1007/s12530-018-9235-y
Volume 11
WOSCitedRecordID wos000563132800008&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: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  customDbUrl:
  eissn: 1868-6486
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002140047
  issn: 1868-6478
  databaseCode: RSV
  dateStart: 20100801
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB60etCDb7G-yMGTsrDZTTabiyCieCpiVXoL-woIpS1NIvTfO5sm1oIKegxMljCZnZmPmfkG4EKhy-cqDYmK4xwBio6JoonDe4X4whqBTpPWyyaSXk8OBuljM8ddtN3ubUmy9tSLYTcWc99EhReU8ZjMVmENo530-xqe-q-tEfGQCd5ycnl3zEJvpvWSFSkk8bOVbXXzu1OX49NycbSOOffb__raHdhqUszgZm4Tu7DiRnuw-YV4cB-u-26Yk6KaeE9ROBuoqhx7Skvf1hxgHhuYYeUpFFA6UCOLj5hk-66i-kcewMv93fPtA2k2KRDDpCyJM9JSzrSh0oV5FCJKYjqxVGiM3qlLaBSlmiK0cNRYkwojZZqHkUlDp-OcC34IndF45I4gyJVCAKu1ETKKfNVNmcg4K6yjFnMr2wXa6i8zDc2433YxzBYEyV41Gaom86rJZl24_HxlMufY-E34qlV41ly34mfp4z9Jn8AG83C6biE7hU45rdwZrJv38q2Yntdm9gHsgssR
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF60CurBt1ifOXhSFjbZZLO5CCKWirWIrdJb2FdAKGlpEqH_3tk0sRZU0GNgsoTJ7Mx8zMw3CF0IcPlURC4WQZAAQJEBFiQ0cK8AX2jFwGmSctlE2O3ywSB6qua4s7rbvS5Jlp56PuzmBdQ2UcEF9WiAp8toxYeAZQnzn3uvtRFR12O05uSy7thzrZmWS1Y449jOVtbVze9OXYxPi8XRMua0tv71tdtos0oxnZuZTeygJZPuoo0vxIN76LpnhgnOirH1FJnRjijykaW0tG3NDuSxjhoWlkIBpB2RaniEJNt2FZU_ch-9tO76t21cbVLAyuM8x0ZxTagnFeHGTXwXUJInQ02YhOgdmZD4fiQJQAtDlFYRU5xHieuryDUySCijB6iRjlJziJxECACwUirGfd9W3YTyldFMG6Iht9JNRGr9xaqiGbfbLobxnCDZqiYG1cRWNfG0iS4_XxnPODZ-E76qFR5X1y37WfroT9LnaK3df-zEnfvuwzFa9yy0LtvJTlAjnxTmFK2q9_wtm5yVJvcBe0fN9Q
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF60iujBt1ifOXhSQje7m83mIohaFKUUqtJb2FdAKGlpUqH_3p00sQoqiMfAZAmTmdn5mJlvEDqTLuRTGQe-DMPUARQV-hJH1vmVwxdGcxc0cblsIup0RL8fd6s9p3nd7V6XJGczDcDSlBWtkUlb88E3ElJoqHLOSmjoTxfREoM-eoDrvZfaoGhAOK35uSA0kwBMtly4IrjwYc6yrnR-d-rXu-probS8f9ob__7yTbRepZ7e1cxWttCCzbbR2idCwh102bOD1M8nI4gguTWenBRDoLqEdmfP5beeHkyAWsFJezIz7tEl39BtVP7gXfTcvn26vvOrDQu-JkIUvtXCYEqUxsIGKQsceiIqMpgrd6vHNsKMxQo7yGGxNjrmWog4DZiOA6vClHK6hxrZMLP7yEuldMBWKc0FY1CNk5ppa7ix2LicyzQRrnWZ6Ip-HLZgDJI5cTKoJnGqSUA1ybSJzj9eGc24N34TvqiVn1RumP8sffAn6VO00r1pJ4_3nYdDtEoAcZddZkeoUYwn9hgt67fiNR-flNb3DuoZ1tk
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=Self-supervised+autoencoders+for+clustering+and+classification&rft.jtitle=Evolving+systems&rft.au=Nousi%2C+Paraskevi&rft.au=Tefas%2C+Anastasios&rft.date=2020-09-01&rft.issn=1868-6478&rft.eissn=1868-6486&rft.volume=11&rft.issue=3&rft.spage=453&rft.epage=466&rft_id=info:doi/10.1007%2Fs12530-018-9235-y&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s12530_018_9235_y
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1868-6478&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1868-6478&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1868-6478&client=summon