WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects

As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers in industry Jg. 142; S. 103720
Hauptverfasser: Nag, Subhrajit, Makwana, Dhruv, R, Sai Chandra Teja, Mittal, Sparsh, Mohan, C.Krishna
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.11.2022
Schlagworte:
ISSN:0166-3615, 1872-6194
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired. The previous works on defect analysis have several limitations, such as low accuracy and the need for separate models for classification and segmentation. For analyzing mixed-type defects, some previous works require separately training one model for each defect type, which is non-scalable. In this paper, we present WaferSegClassNet (WSCN), a novel network based on encoder-decoder architecture. WSCN performs simultaneous classification and segmentation of both single and mixed-type wafer defects. WSCN uses a “shared encoder” for classification, and segmentation, which allows training WSCN end-to-end. We use N-pair contrastive loss to first pretrain the encoder and then use BCE-Dice loss for segmentation, and categorical cross-entropy loss for classification. Use of N-pair contrastive loss helps in better embedding representation in the latent dimension of wafer maps. WSCN has a model size of only 0.51MB and performs only 0.2 M FLOPS. Thus, it is much lighter than other state-of-the-art models. Also, it requires only 150 epochs for convergence, compared to 4000 epochs needed by a previous work. We evaluate our model on the MixedWM38 dataset, which has 38,015 images. WSCN achieves an average classification accuracy of 98.2% and a dice coefficient of 0.9999. We are the first to show segmentation results on the MixedWM38 dataset. The source code can be obtained from https://github.com/ckmvigil/WaferSegClassNet. •Semiconductor Wafer Defect classification and segmentation.•Convolution neural network with encoder-decoder architecture.•A single network which performs both classification and segmentation.•Extremely low model size and computation overhead.•Results on MixedWM38 dataset with 38,015 images.
AbstractList As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since the manual inspection of wafer defects is costly, an automated artificial intelligence (AI) based computer-vision approach is highly desired. The previous works on defect analysis have several limitations, such as low accuracy and the need for separate models for classification and segmentation. For analyzing mixed-type defects, some previous works require separately training one model for each defect type, which is non-scalable. In this paper, we present WaferSegClassNet (WSCN), a novel network based on encoder-decoder architecture. WSCN performs simultaneous classification and segmentation of both single and mixed-type wafer defects. WSCN uses a “shared encoder” for classification, and segmentation, which allows training WSCN end-to-end. We use N-pair contrastive loss to first pretrain the encoder and then use BCE-Dice loss for segmentation, and categorical cross-entropy loss for classification. Use of N-pair contrastive loss helps in better embedding representation in the latent dimension of wafer maps. WSCN has a model size of only 0.51MB and performs only 0.2 M FLOPS. Thus, it is much lighter than other state-of-the-art models. Also, it requires only 150 epochs for convergence, compared to 4000 epochs needed by a previous work. We evaluate our model on the MixedWM38 dataset, which has 38,015 images. WSCN achieves an average classification accuracy of 98.2% and a dice coefficient of 0.9999. We are the first to show segmentation results on the MixedWM38 dataset. The source code can be obtained from https://github.com/ckmvigil/WaferSegClassNet. •Semiconductor Wafer Defect classification and segmentation.•Convolution neural network with encoder-decoder architecture.•A single network which performs both classification and segmentation.•Extremely low model size and computation overhead.•Results on MixedWM38 dataset with 38,015 images.
ArticleNumber 103720
Author Nag, Subhrajit
Makwana, Dhruv
Mohan, C.Krishna
R, Sai Chandra Teja
Mittal, Sparsh
Author_xml – sequence: 1
  givenname: Subhrajit
  surname: Nag
  fullname: Nag, Subhrajit
  organization: IIT Hyderabad, India
– sequence: 2
  givenname: Dhruv
  surname: Makwana
  fullname: Makwana, Dhruv
  organization: CKMVigil Pvt Ltd, India
– sequence: 3
  givenname: Sai Chandra Teja
  surname: R
  fullname: R, Sai Chandra Teja
  email: saichandrateja@ckmvigil.in
  organization: CKMVigil Pvt Ltd, India
– sequence: 4
  givenname: Sparsh
  surname: Mittal
  fullname: Mittal, Sparsh
  organization: IIT Roorkee, India
– sequence: 5
  givenname: C.Krishna
  surname: Mohan
  fullname: Mohan, C.Krishna
  organization: IIT Hyderabad, India
BookMark eNqFkN1KAzEQhYMoWH8eQcgLbE02u0mLF1KKfyB6oeJlyCaTmrpNShItvr1ZtlfeODfDDPMd5pwTdOiDB4QuKJlSQvnleqrDZuu8mdakrsuOiZocoAmdibridN4cokm54xXjtD1GJymtSSkh-AT178pCfIHVslcpPUHGFV7g3q0-crWDoWEPeRfiJ7YhYj1cOeu0yi54rLzBCVYb8HlcBFvmjdPBmy-dC7Ab5LEBCzqnM3RkVZ_gfN9P0dvtzevyvnp8vntYLh4rzUSbq7miihnNjeGMMAbQKVo3tmuhqWtomoYqYedc8I5Q3YFteDE8mxNu26YTTLBTdDXq6hhSimClduODOSrXS0rkEJxcy31wcghOjsEVuv1Db6PbqPjzL3c9clCsfTuIMmkHXoNxsbiXJrh_FH4BjsqPEQ
CitedBy_id crossref_primary_10_1016_j_eswa_2024_125378
crossref_primary_10_1016_j_engappai_2023_105975
crossref_primary_10_1088_2631_8695_adf59b
crossref_primary_10_1088_1361_6501_ac9ed3
crossref_primary_10_3390_electronics13234714
crossref_primary_10_1016_j_eswa_2025_128707
crossref_primary_10_1016_j_isatra_2025_09_005
crossref_primary_10_3390_math12162566
crossref_primary_10_1016_j_eswa_2025_126709
crossref_primary_10_1007_s10845_023_02231_z
crossref_primary_10_1016_j_compind_2023_103963
crossref_primary_10_3390_s25041272
crossref_primary_10_1016_j_asoc_2025_113962
crossref_primary_10_1016_j_eswa_2023_120029
crossref_primary_10_1109_TIM_2025_3527594
crossref_primary_10_1007_s10489_023_04454_2
crossref_primary_10_1016_j_engappai_2025_110121
crossref_primary_10_3390_electronics12081787
crossref_primary_10_1109_ACCESS_2023_3321025
crossref_primary_10_1007_s10845_024_02390_7
crossref_primary_10_1007_s11227_025_07521_2
crossref_primary_10_1109_ACCESS_2025_3528242
crossref_primary_10_1109_TIM_2024_3395316
crossref_primary_10_1109_TCAD_2023_3274958
crossref_primary_10_1016_j_ress_2025_111637
crossref_primary_10_1016_j_compind_2023_103990
crossref_primary_10_1016_j_engappai_2024_109707
crossref_primary_10_1109_ACCESS_2024_3525408
crossref_primary_10_1016_j_cie_2024_110486
crossref_primary_10_1007_s10845_024_02377_4
crossref_primary_10_1016_j_cie_2024_110187
crossref_primary_10_3390_s24103144
crossref_primary_10_1007_s10845_023_02242_w
crossref_primary_10_1007_s11668_025_02227_2
crossref_primary_10_1109_ACCESS_2025_3546781
crossref_primary_10_1038_s41598_025_86323_1
crossref_primary_10_1016_j_eswa_2025_127121
crossref_primary_10_1038_s41598_024_78578_x
crossref_primary_10_1088_1361_6501_adbc0d
crossref_primary_10_1016_j_iswa_2025_200576
crossref_primary_10_3390_s23208502
Cites_doi 10.1016/j.patrec.2018.12.013
10.1109/TPAMI.2017.2699184
10.1080/00401706.1997.10485116
10.3390/en11051221
10.1016/j.ijleo.2019.163038
10.1109/TSM.2018.2795466
10.1109/TPAMI.2016.2644615
10.1186/s12864-019-6413-7
10.1109/TSM.2018.2825482
10.1080/07408170600733236
10.1109/TSM.2020.3020985
10.1002/int.22386
10.1109/TSM.2018.2841416
10.1109/TSM.2008.2005375
10.1109/5.726791
10.1016/S0026-2714(98)00127-9
10.1109/TSM.2018.2806931
10.1109/TSM.2019.2897690
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.compind.2022.103720
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1872-6194
ExternalDocumentID 10_1016_j_compind_2022_103720
S0166361522001178
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABUCO
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACGOD
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AI.
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
APLSM
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BKOMP
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HAMUX
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
R2-
RIG
RNS
ROL
RPZ
RXW
SBC
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SSB
SSD
SST
SSV
SSZ
T5K
TAE
TAF
TN5
U5U
UNMZH
VH1
WH7
WUQ
XPP
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c375t-9a1a3dc6dd63033eeba124fb5e422e4441a7f9676b01cbef463728906f54b7373
ISICitedReferencesCount 55
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000832981000003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0166-3615
IngestDate Sat Nov 29 07:24:35 EST 2025
Tue Nov 18 22:23:51 EST 2025
Fri Feb 23 02:40:25 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Semiconductor wafer defect analysis
Encoder-decoder architecture
Convolution neural network
Image Segmentation
Image classification
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c375t-9a1a3dc6dd63033eeba124fb5e422e4441a7f9676b01cbef463728906f54b7373
ParticipantIDs crossref_citationtrail_10_1016_j_compind_2022_103720
crossref_primary_10_1016_j_compind_2022_103720
elsevier_sciencedirect_doi_10_1016_j_compind_2022_103720
PublicationCentury 2000
PublicationDate November 2022
2022-11-00
PublicationDateYYYYMMDD 2022-11-01
PublicationDate_xml – month: 11
  year: 2022
  text: November 2022
PublicationDecade 2020
PublicationTitle Computers in industry
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Tan, Le,Efficientnet (bib29) 2019
Zhang, Sabuncu (bib34) 2018; 31
Long, Shelhamer, Darrell (bib17) 2015
Badrinarayanan, Kendall, Cipolla (bib4) 2017; 39
Sciuto, Napoli, Capizzi, Shikler (bib27) 2019; 194
Sohn (bib28) 2016; 29
Huang, Liu, Van Der Maaten, Weinberger (bib12) 2017
Hansen, Thyregod (bib9) 1998; 38
He, Zhang, Ren, Sun (bib11) 2016
Wang, Xu, Yang, Zhang, Li (bib32) 2020; 33
Capizzi, LoSciuto, Napoli, Shikler, Woźniak (bib5) 2018; 11
anonymousF1/dice-score vs iou, 2022
Sandler, Howard, Zhu, Zhmoginov, Chen (bib26) 2018
Jeong, Kim, Jeong (bib13) 2008; 21
Piao, Jin, Lee, Byun (bib23) 2018; 31
Wang, Kuo, Bensmail (bib31) 2006; 38
LeCun, Bottou, Bengio, Haffner (bib16) 1998; 86
Nakazawa, Kulkarni (bib21) 2018; 31
Nakazawa, Kulkarni (bib22) 2019; 32
Saad, Sabri, Hasan, Ali, Saleh (bib25) 2015; 815
LoSciuto, Capizzi, Shikler, Napoli (bib18) 2021; 36
Ronneberger, Fischer, Brox (bib24) 2015
Chen, Papandreou, Kokkinos, Murphy, Yuille (bib6) 2017; 40
Kyeong, Kim (bib15) 2018; 31
Maksim, Kirill, Eduard, Nikita, Aleksandr, Arina, Vladislav, Daniil, Nikolay (bib19) 2019
.
Wu, Jang, Chen (bib33) 2014; 28
Han, Gao, Zhao, Liao, Tang, Li (bib8) 2020; 130
Krizhevsky, Sutskever, Hinton (bib14) 2012; 25
Mittal, Srivastava, Jayanth (bib20) 2022
Chicco, Jurman (bib7) 2020; 21
Tello, Al-Jarrah, Yoo, Al-Hammadi, Muhaidat, Lee (bib30) 2018; 31
Hansen, Nair, Friedman (bib10) 1997; 39
anonymous 2022
Chicco (10.1016/j.compind.2022.103720_bib7) 2020; 21
Huang (10.1016/j.compind.2022.103720_bib12) 2017
Han (10.1016/j.compind.2022.103720_bib8) 2020; 130
Wang (10.1016/j.compind.2022.103720_bib31) 2006; 38
Jeong (10.1016/j.compind.2022.103720_bib13) 2008; 21
LeCun (10.1016/j.compind.2022.103720_bib16) 1998; 86
Sohn (10.1016/j.compind.2022.103720_bib28) 2016; 29
Tello (10.1016/j.compind.2022.103720_bib30) 2018; 31
Wu (10.1016/j.compind.2022.103720_bib33) 2014; 28
Nakazawa (10.1016/j.compind.2022.103720_bib22) 2019; 32
Chen (10.1016/j.compind.2022.103720_bib6) 2017; 40
Maksim (10.1016/j.compind.2022.103720_bib19) 2019
Kyeong (10.1016/j.compind.2022.103720_bib15) 2018; 31
Badrinarayanan (10.1016/j.compind.2022.103720_bib4) 2017; 39
Sandler (10.1016/j.compind.2022.103720_bib26) 2018
He (10.1016/j.compind.2022.103720_bib11) 2016
Tan (10.1016/j.compind.2022.103720_bib29) 2019
Krizhevsky (10.1016/j.compind.2022.103720_bib14) 2012; 25
Hansen (10.1016/j.compind.2022.103720_bib9) 1998; 38
10.1016/j.compind.2022.103720_bib3
Nakazawa (10.1016/j.compind.2022.103720_bib21) 2018; 31
Zhang (10.1016/j.compind.2022.103720_bib34) 2018; 31
10.1016/j.compind.2022.103720_bib2
Capizzi (10.1016/j.compind.2022.103720_bib5) 2018; 11
10.1016/j.compind.2022.103720_bib1
Piao (10.1016/j.compind.2022.103720_bib23) 2018; 31
Saad (10.1016/j.compind.2022.103720_bib25) 2015; 815
Sciuto (10.1016/j.compind.2022.103720_bib27) 2019; 194
Wang (10.1016/j.compind.2022.103720_bib32) 2020; 33
Mittal (10.1016/j.compind.2022.103720_bib20) 2022
LoSciuto (10.1016/j.compind.2022.103720_bib18) 2021; 36
Ronneberger (10.1016/j.compind.2022.103720_bib24) 2015
Hansen (10.1016/j.compind.2022.103720_bib10) 1997; 39
Long (10.1016/j.compind.2022.103720_bib17) 2015
References_xml – volume: 31
  start-page: 309
  year: 2018
  end-page: 314
  ident: bib21
  article-title: Wafer map defect pattern classification and image retrieval using convolutional neural network
  publication-title: IEEE Trans. Semicond. Manuf.
– volume: 21
  start-page: 1
  year: 2020
  end-page: 13
  ident: bib7
  article-title: The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation
  publication-title: BMC Genom.
– start-page: 770
  year: 2016
  end-page: 778
  ident: bib11
  article-title: Deep residual learning for image recognition
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 86
  start-page: 2278
  year: 1998
  end-page: 2324
  ident: bib16
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proc. IEEE
– volume: 36
  start-page: 2443
  year: 2021
  end-page: 2464
  ident: bib18
  article-title: Organic solar cells defects classification by using a new feature extraction algorithm and an ebnn with an innovative pruning algorithm
  publication-title: Int. J. Intell. Syst.
– volume: 31
  start-page: 250
  year: 2018
  end-page: 257
  ident: bib23
  article-title: Decision tree ensemble-based wafer map failure pattern recognition based on radon transform-based features
  publication-title: IEEE Trans. Semicond. Manuf.
– start-page: 4700
  year: 2017
  end-page: 4708
  ident: bib12
  article-title: Densely connected convolutional networks
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 25
  year: 2012
  ident: bib14
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 4510
  year: 2018
  end-page: 4520
  ident: bib26
  article-title: Mobilenetv2: Inverted residuals and linear bottlenecks, in
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– start-page: 6105
  year: 2019
  end-page: 6114
  ident: bib29
  article-title: Rethinking model scaling for convolutional neural networks
  publication-title: Int. Conf. Mach. Learn. PMLR
– start-page: 3431
  year: 2015
  end-page: 3440
  ident: bib17
  article-title: Fully convolutional networks for semantic segmentation, in
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 31
  start-page: 315
  year: 2018
  end-page: 322
  ident: bib30
  article-title: Deep-structured machine learning model for the recognition of mixed-defect patterns in semiconductor fabrication processes
  publication-title: IEEE Trans. Semicond. Manuf.
– reference: anonymous 2022
– reference: anonymousF1/dice-score vs iou, 2022
– volume: 11
  start-page: 1221
  year: 2018
  ident: bib5
  article-title: Optimizing the organic solar cell manufacturing process by means of afm measurements and neural networks
  publication-title: Energies
– volume: 38
  start-page: 1155
  year: 1998
  end-page: 1164
  ident: bib9
  article-title: Use of wafer maps in integrated circuit manufacturing
  publication-title: Microelectron. Reliab.
– volume: 39
  start-page: 241
  year: 1997
  end-page: 253
  ident: bib10
  article-title: Monitoring wafer map data from integrated circuit fabrication processes for spatially clustered defects
  publication-title: Technometrics
– volume: 29
  year: 2016
  ident: bib28
  article-title: Improved deep metric learning with multi-class n-pair loss objective
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 31
  start-page: 395
  year: 2018
  end-page: 402
  ident: bib15
  article-title: Classification of mixed-type defect patterns in wafer bin maps using convolutional neural networks
  publication-title: IEEE Trans. Semicond. Manuf.
– volume: 40
  start-page: 834
  year: 2017
  end-page: 848
  ident: bib6
  article-title: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 815
  start-page: 374
  year: 2015
  end-page: 379
  ident: bib25
  article-title: Defect segmentation of semiconductor wafer image using k-means clustering, in Applied Mechanics and Materials
  publication-title: Trans. Tech. Publ.
– volume: 130
  start-page: 234
  year: 2020
  end-page: 241
  ident: bib8
  article-title: Polycrystalline silicon wafer defect segmentation based on deep convolutional neural networks
  publication-title: Pattern Recognit. Lett.
– start-page: 1
  year: 2019
  end-page: 5
  ident: bib19
  article-title: Classification of wafer maps defect based on deep learning methods with small amount of data
  publication-title: 2019 Int. Conf. Eng. Telecommun. (EnT). IEEE Dolgoprudny: Russ.
– volume: 21
  start-page: 625
  year: 2008
  end-page: 637
  ident: bib13
  article-title: Automatic identification of defect patterns in semiconductor wafer maps using spatial correlogram and dynamic time warping
  publication-title: IEEE Trans. Semicond. Manuf.
– volume: 31
  year: 2018
  ident: bib34
  article-title: Generalized cross entropy loss for training deep neural networks with noisy labels
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: .
– start-page: 234
  year: 2015
  end-page: 241
  ident: bib24
  article-title: U-net: Convolutional Networks For Biomedical Image Segmentation
  publication-title: International Conference on Medical image computing and computer-assisted intervention
– volume: 39
  start-page: 2481
  year: 2017
  end-page: 2495
  ident: bib4
  article-title: Segnet: a deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2022
  ident: bib20
  article-title: A survey of deep learning techniques for underwater image classification
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 32
  start-page: 250
  year: 2019
  end-page: 256
  ident: bib22
  article-title: Anomaly detection and segmentation for wafer defect patterns using deep convolutional encoder-decoder neural network architectures in semiconductor manufacturing
  publication-title: IEEE Trans. Semicond. Manuf.
– volume: 28
  start-page: 1
  year: 2014
  end-page: 12
  ident: bib33
  article-title: Wafer map failure pattern recognition and similarity ranking for large-scale data sets
  publication-title: IEEE Trans. Semicond. Manuf.
– volume: 38
  start-page: 1059
  year: 2006
  end-page: 1068
  ident: bib31
  article-title: Detection and classification of defect patterns on semiconductor wafers
  publication-title: IIE Trans.
– volume: 194
  year: 2019
  ident: bib27
  article-title: Organic solar cells defects detection by means of an elliptical basis neural network and a new feature extraction technique
  publication-title: Optik
– volume: 33
  start-page: 587
  year: 2020
  end-page: 596
  ident: bib32
  article-title: Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition
  publication-title: IEEE Trans. Semicond. Manuf.
– year: 2022
  ident: 10.1016/j.compind.2022.103720_bib20
  article-title: A survey of deep learning techniques for underwater image classification
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– start-page: 3431
  year: 2015
  ident: 10.1016/j.compind.2022.103720_bib17
  article-title: Fully convolutional networks for semantic segmentation, in
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 130
  start-page: 234
  year: 2020
  ident: 10.1016/j.compind.2022.103720_bib8
  article-title: Polycrystalline silicon wafer defect segmentation based on deep convolutional neural networks
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2018.12.013
– start-page: 234
  year: 2015
  ident: 10.1016/j.compind.2022.103720_bib24
  article-title: U-net: Convolutional Networks For Biomedical Image Segmentation
– volume: 40
  start-page: 834
  issue: 4
  year: 2017
  ident: 10.1016/j.compind.2022.103720_bib6
  article-title: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2017.2699184
– volume: 29
  year: 2016
  ident: 10.1016/j.compind.2022.103720_bib28
  article-title: Improved deep metric learning with multi-class n-pair loss objective
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 39
  start-page: 241
  issue: 3
  year: 1997
  ident: 10.1016/j.compind.2022.103720_bib10
  article-title: Monitoring wafer map data from integrated circuit fabrication processes for spatially clustered defects
  publication-title: Technometrics
  doi: 10.1080/00401706.1997.10485116
– volume: 11
  start-page: 1221
  issue: 5
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib5
  article-title: Optimizing the organic solar cell manufacturing process by means of afm measurements and neural networks
  publication-title: Energies
  doi: 10.3390/en11051221
– ident: 10.1016/j.compind.2022.103720_bib1
– volume: 28
  start-page: 1
  issue: 1
  year: 2014
  ident: 10.1016/j.compind.2022.103720_bib33
  article-title: Wafer map failure pattern recognition and similarity ranking for large-scale data sets
  publication-title: IEEE Trans. Semicond. Manuf.
– ident: 10.1016/j.compind.2022.103720_bib3
– volume: 194
  year: 2019
  ident: 10.1016/j.compind.2022.103720_bib27
  article-title: Organic solar cells defects detection by means of an elliptical basis neural network and a new feature extraction technique
  publication-title: Optik
  doi: 10.1016/j.ijleo.2019.163038
– volume: 31
  start-page: 309
  issue: 2
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib21
  article-title: Wafer map defect pattern classification and image retrieval using convolutional neural network
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2018.2795466
– volume: 39
  start-page: 2481
  issue: 12
  year: 2017
  ident: 10.1016/j.compind.2022.103720_bib4
  article-title: Segnet: a deep convolutional encoder-decoder architecture for image segmentation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2016.2644615
– volume: 21
  start-page: 1
  issue: 1
  year: 2020
  ident: 10.1016/j.compind.2022.103720_bib7
  article-title: The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation
  publication-title: BMC Genom.
  doi: 10.1186/s12864-019-6413-7
– start-page: 770
  year: 2016
  ident: 10.1016/j.compind.2022.103720_bib11
  article-title: Deep residual learning for image recognition
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– start-page: 4510
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib26
  article-title: Mobilenetv2: Inverted residuals and linear bottlenecks, in
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 31
  start-page: 315
  issue: 2
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib30
  article-title: Deep-structured machine learning model for the recognition of mixed-defect patterns in semiconductor fabrication processes
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2018.2825482
– start-page: 4700
  year: 2017
  ident: 10.1016/j.compind.2022.103720_bib12
  article-title: Densely connected convolutional networks
  publication-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit.
– volume: 31
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib34
  article-title: Generalized cross entropy loss for training deep neural networks with noisy labels
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 815
  start-page: 374
  year: 2015
  ident: 10.1016/j.compind.2022.103720_bib25
  article-title: Defect segmentation of semiconductor wafer image using k-means clustering, in Applied Mechanics and Materials
  publication-title: Trans. Tech. Publ.
– volume: 38
  start-page: 1059
  issue: 12
  year: 2006
  ident: 10.1016/j.compind.2022.103720_bib31
  article-title: Detection and classification of defect patterns on semiconductor wafers
  publication-title: IIE Trans.
  doi: 10.1080/07408170600733236
– volume: 33
  start-page: 587
  issue: 4
  year: 2020
  ident: 10.1016/j.compind.2022.103720_bib32
  article-title: Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2020.3020985
– volume: 36
  start-page: 2443
  issue: 6
  year: 2021
  ident: 10.1016/j.compind.2022.103720_bib18
  article-title: Organic solar cells defects classification by using a new feature extraction algorithm and an ebnn with an innovative pruning algorithm
  publication-title: Int. J. Intell. Syst.
  doi: 10.1002/int.22386
– volume: 31
  start-page: 395
  issue: 3
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib15
  article-title: Classification of mixed-type defect patterns in wafer bin maps using convolutional neural networks
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2018.2841416
– volume: 21
  start-page: 625
  issue: 4
  year: 2008
  ident: 10.1016/j.compind.2022.103720_bib13
  article-title: Automatic identification of defect patterns in semiconductor wafer maps using spatial correlogram and dynamic time warping
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2008.2005375
– volume: 86
  start-page: 2278
  issue: 11
  year: 1998
  ident: 10.1016/j.compind.2022.103720_bib16
  article-title: Gradient-based learning applied to document recognition
  publication-title: Proc. IEEE
  doi: 10.1109/5.726791
– ident: 10.1016/j.compind.2022.103720_bib2
– volume: 25
  year: 2012
  ident: 10.1016/j.compind.2022.103720_bib14
  article-title: Imagenet classification with deep convolutional neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 38
  start-page: 1155
  issue: 6–8
  year: 1998
  ident: 10.1016/j.compind.2022.103720_bib9
  article-title: Use of wafer maps in integrated circuit manufacturing
  publication-title: Microelectron. Reliab.
  doi: 10.1016/S0026-2714(98)00127-9
– volume: 31
  start-page: 250
  issue: 2
  year: 2018
  ident: 10.1016/j.compind.2022.103720_bib23
  article-title: Decision tree ensemble-based wafer map failure pattern recognition based on radon transform-based features
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2018.2806931
– volume: 32
  start-page: 250
  issue: 2
  year: 2019
  ident: 10.1016/j.compind.2022.103720_bib22
  article-title: Anomaly detection and segmentation for wafer defect patterns using deep convolutional encoder-decoder neural network architectures in semiconductor manufacturing
  publication-title: IEEE Trans. Semicond. Manuf.
  doi: 10.1109/TSM.2019.2897690
– start-page: 1
  year: 2019
  ident: 10.1016/j.compind.2022.103720_bib19
  article-title: Classification of wafer maps defect based on deep learning methods with small amount of data
  publication-title: 2019 Int. Conf. Eng. Telecommun. (EnT). IEEE Dolgoprudny: Russ.
– start-page: 6105
  year: 2019
  ident: 10.1016/j.compind.2022.103720_bib29
  article-title: Rethinking model scaling for convolutional neural networks
  publication-title: Int. Conf. Mach. Learn. PMLR
SSID ssj0000776
Score 2.5888376
Snippet As the integration density and design intricacy of semiconductor wafers increase, the magnitude and complexity of defects in them are also on the rise. Since...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 103720
SubjectTerms Convolution neural network
Encoder-decoder architecture
Image classification
Image Segmentation
Semiconductor wafer defect analysis
Title WaferSegClassNet - A light-weight network for classification and segmentation of semiconductor wafer defects
URI https://dx.doi.org/10.1016/j.compind.2022.103720
Volume 142
WOSCitedRecordID wos000832981000003&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: ScienceDirect database
  customDbUrl:
  eissn: 1872-6194
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000776
  issn: 0166-3615
  databaseCode: AIEXJ
  dateStart: 19950301
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELbKLgc4rHhqlwXkA7fKpc3Ddo4VLALEVkgt0Fvk2M42paRVNm33L_CvGdtJmrIrXhKXqIo6djvzxf48mQdCL6RIgIfrlPRVEJHAk5SIKBBEKhkqzZOU2xftnz-w0YhPp9HHTud7nQuzWbA851dX0eq_mhrugbFN6uxfmLsZFG7AZzA6XMHscP0jw38RqS7G-sK2uxzpskvg4V_YeiFb6wft5i7020YYSvMtEy7kgGDd6PriW5WRZLnkpYmfX-amMCwIbM3wXaVtGEib2tb9IWyAbeY6gjT--pFwXul1MivEPGtibc7F161waWmvZ8V607z_cd7qzGY_qEJ0J3rebCDnWVnaPgXd8QrO5bO25wIOvYM9z8X1lBrn4aSU-NTlePa0W5U584hxt-wt264q17UtwHkj5saCK_izPTOzLS3g9Xd7XhOJODbzmek8z5bH47fQocfCCBbIw-G7s-n73bbObKfC5vft0sFe3jjZzUSnRV4m99BRderAQ4eW-6ij8wfobqsW5UO0-Bk3mOAhbuMGV7jBgBu8jxsMRsJt3OBlivdwgy1ucIWbR-jTm7PJq7ekasVBpM_CkkRiIHwlqVIUOI-vdSKAGKZJqAPP0wFwasHSiDKa9Acy0WlAQQU86tM0DBLmM_8xOsiXuT5GeKAYpwLUnVIeKGE6KkgFRNiLBFUwwgkKar3FsqpTb9qlLOI6IHEeV-qOjbpjp-4T1GvEVq5Qy-8EeG2UuGKbjkXGgKRfiz75d9FTdGf3KDxFB2Wx1s_Qbbkps8vieYW5H5gDqmQ
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=WaferSegClassNet+-+A+light-weight+network+for+classification+and+segmentation+of+semiconductor+wafer+defects&rft.jtitle=Computers+in+industry&rft.au=Nag%2C+Subhrajit&rft.au=Makwana%2C+Dhruv&rft.au=R%2C+Sai+Chandra+Teja&rft.au=Mittal%2C+Sparsh&rft.date=2022-11-01&rft.pub=Elsevier+B.V&rft.issn=0166-3615&rft.eissn=1872-6194&rft.volume=142&rft_id=info:doi/10.1016%2Fj.compind.2022.103720&rft.externalDocID=S0166361522001178
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0166-3615&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0166-3615&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0166-3615&client=summon