Pros and cons of GAN evaluation measures: New developments

This work is an update of my previous paper on the same topic published a few years ago (Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative and qualitative techniques to evaluate models has emerged. Although some measures such as Inception Score, Fréchet Inc...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Computer vision and image understanding Ročník 215; s. 103329
Hlavní autor: Borji, Ali
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.01.2022
Témata:
ISSN:1077-3142, 1090-235X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This work is an update of my previous paper on the same topic published a few years ago (Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative and qualitative techniques to evaluate models has emerged. Although some measures such as Inception Score, Fréchet Inception Distance, Precision–Recall, and Perceptual Path Length are relatively more popular, GAN evaluation is not a settled issue and there is still room for improvement. Here, I describe new dimensions that are becoming important in assessing models (e.g. bias and fairness) and discuss the connection between GAN evaluation and deepfakes. These are important areas of concern in the machine learning community today and progress in GAN evaluation can help mitigate them. •A critical review of new techniques for evaluating generative models.•A discussion of bias and fairness in the context of GANs and ways to mitigate them.•A discussion of how realistic deepfakes are and approaches to detect them.
AbstractList This work is an update of my previous paper on the same topic published a few years ago (Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative and qualitative techniques to evaluate models has emerged. Although some measures such as Inception Score, Fréchet Inception Distance, Precision–Recall, and Perceptual Path Length are relatively more popular, GAN evaluation is not a settled issue and there is still room for improvement. Here, I describe new dimensions that are becoming important in assessing models (e.g. bias and fairness) and discuss the connection between GAN evaluation and deepfakes. These are important areas of concern in the machine learning community today and progress in GAN evaluation can help mitigate them. •A critical review of new techniques for evaluating generative models.•A discussion of bias and fairness in the context of GANs and ways to mitigate them.•A discussion of how realistic deepfakes are and approaches to detect them.
ArticleNumber 103329
Author Borji, Ali
Author_xml – sequence: 1
  givenname: Ali
  orcidid: 0000-0001-8198-0335
  surname: Borji
  fullname: Borji, Ali
  email: aliborji@gmail.com
  organization: Quintic AI, San Francisco, CA, USA
BookMark eNp9kLFOwzAQhi1UJNrCCzD5BVJsJ6mdiqWqoCBVhaEDm-WcL5KrNK7sNIi3J2mZGDrd6aTv13_fhIwa3yAhj5zNOOPzp_0MOneaCSZ4f0hTUdyQMWcFS0Saf42GXcok5Zm4I5MY94xxnhV8TBafwUdqGkvBN5H6iq6XW4qdqU-mdb6hBzTxFDAu6Ba_qcUOa388YNPGe3JbmTriw9-ckt3ry271lmw-1u-r5SaBlLE2UazkAJxZm2WVAJGhEXkOFm2FAKWSvMxsrgqlyrJkJpNqLvvSICWakmE6JeoSC33TGLDS4NpztzYYV2vO9KBA7_WgQA8K9EVBj4p_6DG4gwk_16HnC4T9T53DoCM4bACtCwittt5dw38BaX93vA
CitedBy_id crossref_primary_10_1007_s10334_023_01127_6
crossref_primary_10_3390_s24041229
crossref_primary_10_3390_s22197534
crossref_primary_10_1002_mp_17801
crossref_primary_10_1007_s10999_024_09711_x
crossref_primary_10_1177_15353702221121602
crossref_primary_10_3390_s22041565
crossref_primary_10_1109_TMI_2024_3414931
crossref_primary_10_1109_ACCESS_2024_3370848
crossref_primary_10_1016_j_bbe_2025_09_001
crossref_primary_10_1016_j_jasc_2022_10_001
crossref_primary_10_1016_j_engappai_2025_111032
crossref_primary_10_1016_j_trd_2024_104067
crossref_primary_10_1016_j_media_2024_103106
crossref_primary_10_1016_j_conbuildmat_2025_143369
crossref_primary_10_1016_j_neucom_2025_129750
crossref_primary_10_1109_TEVC_2023_3338371
crossref_primary_10_1016_j_ascom_2025_100990
crossref_primary_10_1080_15376494_2023_2198528
crossref_primary_10_1002_mp_17473
crossref_primary_10_1080_13682199_2024_2395749
crossref_primary_10_1145_3769106
crossref_primary_10_1109_ACCESS_2024_3366801
crossref_primary_10_1109_TCC_2024_3459789
crossref_primary_10_3390_app14209586
crossref_primary_10_3390_s23031450
crossref_primary_10_1109_ACCESS_2022_3228552
crossref_primary_10_3390_ijgi12060245
crossref_primary_10_1007_s11042_025_20612_9
crossref_primary_10_1016_j_jmbbm_2025_107116
crossref_primary_10_1016_j_compbiomed_2024_109414
crossref_primary_10_1029_2024JE008739
crossref_primary_10_3390_math11040977
crossref_primary_10_1016_j_foodcont_2024_110790
crossref_primary_10_1109_JSTARS_2025_3590446
crossref_primary_10_1016_j_compgeo_2025_107177
crossref_primary_10_3389_fcomp_2024_1260604
crossref_primary_10_1016_j_patrec_2024_08_023
crossref_primary_10_1038_s42256_024_00889_5
crossref_primary_10_1109_ACCESS_2024_3518979
crossref_primary_10_1093_jcde_qwae061
crossref_primary_10_1007_s10278_023_00951_5
crossref_primary_10_1016_j_ijleo_2022_169607
crossref_primary_10_3390_diagnostics14161756
crossref_primary_10_1038_s41598_025_87358_0
crossref_primary_10_1007_s00138_025_01732_6
crossref_primary_10_3390_app12104844
crossref_primary_10_1002_mp_17931
crossref_primary_10_1016_j_engappai_2025_110133
crossref_primary_10_1109_ACCESS_2025_3547255
crossref_primary_10_1109_TAI_2024_3440219
crossref_primary_10_1016_j_jobe_2025_113365
crossref_primary_10_1016_j_jocs_2025_102539
crossref_primary_10_1109_TSE_2022_3202311
crossref_primary_10_3390_electronics13173462
crossref_primary_10_1016_j_compag_2022_107208
crossref_primary_10_1145_3666006
crossref_primary_10_3390_s25082477
crossref_primary_10_3390_make6030073
crossref_primary_10_4018_JOEUC_371759
crossref_primary_10_1016_j_scitotenv_2024_172578
crossref_primary_10_1016_j_energy_2025_135423
crossref_primary_10_1080_15481603_2024_2364460
crossref_primary_10_1016_j_commatsci_2023_112512
crossref_primary_10_1007_s10278_025_01536_0
crossref_primary_10_1038_s41576_023_00636_3
crossref_primary_10_1021_jacs_2c13467
crossref_primary_10_1109_ACCESS_2024_3354724
crossref_primary_10_1186_s40537_024_00924_7
crossref_primary_10_1002_widm_70038
crossref_primary_10_1109_ACCESS_2024_3368612
crossref_primary_10_3390_electronics11060837
crossref_primary_10_1007_s12243_023_00980_9
crossref_primary_10_1016_j_compag_2024_108762
crossref_primary_10_3390_electronics13020395
crossref_primary_10_1016_j_eswa_2024_124341
crossref_primary_10_1007_s10994_024_06701_0
crossref_primary_10_1016_j_cad_2023_103498
crossref_primary_10_1016_j_cviu_2023_103768
crossref_primary_10_1109_TKDE_2024_3361474
crossref_primary_10_1016_j_jobe_2024_110320
crossref_primary_10_1109_JSTARS_2024_3361444
crossref_primary_10_1007_s13534_024_00409_9
crossref_primary_10_1038_s41598_024_83975_3
crossref_primary_10_1088_2632_2153_adb3ee
crossref_primary_10_1093_mnras_stad2778
crossref_primary_10_1007_s13748_024_00359_4
crossref_primary_10_29220_CSAM_2025_32_2_235
crossref_primary_10_1007_s11042_024_19361_y
crossref_primary_10_1016_j_neucom_2025_129422
crossref_primary_10_1088_1674_1056_ad23d8
crossref_primary_10_3390_app14156831
crossref_primary_10_1016_j_ymssp_2023_110370
crossref_primary_10_1016_j_ejrai_2025_100030
crossref_primary_10_1029_2024JH000533
crossref_primary_10_1007_s10278_024_01205_8
crossref_primary_10_1016_j_commatsci_2023_112074
crossref_primary_10_1038_s44172_025_00450_1
crossref_primary_10_1016_j_eswa_2024_125576
crossref_primary_10_1016_j_cosrev_2024_100662
crossref_primary_10_1016_j_energy_2025_134711
crossref_primary_10_3390_su17125255
crossref_primary_10_1103_PhysRevApplied_21_044032
crossref_primary_10_3390_info12090375
crossref_primary_10_1016_j_image_2025_117307
crossref_primary_10_1007_s43681_022_00161_9
crossref_primary_10_1109_ACCESS_2024_3505989
crossref_primary_10_3348_kjr_2024_0392
crossref_primary_10_1007_s11227_024_06198_3
crossref_primary_10_1080_10447318_2025_2531286
crossref_primary_10_1088_2632_2153_acee44
crossref_primary_10_1093_ptep_ptae106
crossref_primary_10_1038_s41551_025_01468_8
crossref_primary_10_17163_ings_n34_2025_09
crossref_primary_10_1016_j_cad_2023_103609
crossref_primary_10_1093_insilicoplants_diaf002
crossref_primary_10_3233_JIFS_219373
crossref_primary_10_1109_TVT_2022_3216028
crossref_primary_10_1007_s10489_023_04644_y
crossref_primary_10_1016_j_engstruct_2025_120276
crossref_primary_10_1109_TIFS_2025_3560557
crossref_primary_10_1145_3559540
crossref_primary_10_3390_electronics13030476
crossref_primary_10_1016_j_cma_2025_118064
crossref_primary_10_1016_j_heliyon_2024_e26466
crossref_primary_10_1016_j_jmb_2025_169181
crossref_primary_10_1007_s42979_025_03867_9
crossref_primary_10_1111_1556_4029_15680
crossref_primary_10_1088_2632_2153_ad9a3a
crossref_primary_10_1016_j_engappai_2023_107255
crossref_primary_10_1016_j_physd_2023_133831
crossref_primary_10_1088_2058_9565_acd578
crossref_primary_10_1109_ACCESS_2025_3588762
crossref_primary_10_1007_s42484_023_00135_y
crossref_primary_10_1016_j_imavis_2023_104771
Cites_doi 10.1016/j.neunet.2020.07.007
10.1109/CVPR.2018.00068
10.1021/acs.jcim.8b00234
10.1007/978-3-030-01249-6_13
10.1016/j.inffus.2020.06.014
10.1007/978-3-030-01234-2_32
10.1109/CVPR42600.2020.00813
10.1007/s12559-019-09670-y
10.1016/j.proeng.2013.09.086
10.1147/JRD.2019.2945519
10.23915/distill.00018
10.1109/CVPR.2019.00453
10.1109/ICCV.2015.425
10.1016/j.cviu.2018.10.009
10.1109/ICCV.2019.00765
10.1109/CVPR.2019.00244
10.1109/CVPR.2018.00165
10.1109/CVPR42600.2020.00872
10.1109/JPROC.2021.3049196
10.1145/325334.325242
10.1109/ICCV.2019.00460
10.1109/CVPR.2017.502
10.1109/CVPR42600.2020.00611
10.1109/CVPR42600.2020.00791
ContentType Journal Article
Copyright 2021 Elsevier Inc.
Copyright_xml – notice: 2021 Elsevier Inc.
DBID AAYXX
CITATION
DOI 10.1016/j.cviu.2021.103329
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1090-235X
ExternalDocumentID 10_1016_j_cviu_2021_103329
S1077314221001685
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
29F
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKC
AAIKJ
AAKOC
AALRI
AAMNW
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABEFU
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADFGL
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CAG
COF
CS3
DM4
DU5
EBS
EFBJH
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HF~
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
LG5
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
RNS
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSV
SSZ
T5K
TN5
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
SST
~HD
ID FETCH-LOGICAL-c300t-80b1cc10dd44f2c24ea255cdedfeccb871b4d58988bbb0a47867235c77eab0e3
ISICitedReferencesCount 189
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000736276200004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1077-3142
IngestDate Tue Nov 18 21:01:46 EST 2025
Sat Nov 29 07:05:22 EST 2025
Fri Feb 23 02:41:11 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Generative modeling
Deepfakes
GAN evaluation
41A10
65D05
65D17
41A05
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-80b1cc10dd44f2c24ea255cdedfeccb871b4d58988bbb0a47867235c77eab0e3
ORCID 0000-0001-8198-0335
ParticipantIDs crossref_citationtrail_10_1016_j_cviu_2021_103329
crossref_primary_10_1016_j_cviu_2021_103329
elsevier_sciencedirect_doi_10_1016_j_cviu_2021_103329
PublicationCentury 2000
PublicationDate January 2022
2022-01-00
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: January 2022
PublicationDecade 2020
PublicationTitle Computer vision and image understanding
PublicationYear 2022
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Roblek, Kilgour, Sharifi, Zuluaga (b65) 2019
Verma, Rubin (b82) 2018
Djolonga, Lucic, Cuturi, Bachem, Bousquet, Gelly (b22) 2020
Tulyakov, S., Liu, M.-Y., Yang, X., Kautz, J., 2018. Mocogan: Decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1526–1535.
Yu, Seff, Zhang, Song, Funkhouser, Xiao (b91) 2015
Theis, Oord, Bethge (b77) 2015
Ramesh, Pavlov, Goh, Gray, Voss, Radford, Chen, Sutskever (b62) 2021
Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y., 2019. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2337–2346.
Sajjadi, Bachem, Lucic, Bousquet, Gelly (b66) 2018
Wang, She, Ward (b84) 2019
McDuff, Ma, Song, Kapoor (b49) 2019
Simonyan, Zisserman (b73) 2014
Buolamwini, Gebru (b12) 2018
Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O., 2018. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 586–595.
Iqbal, Qureshi (b33) 2020
Chai, Bau, Lim, Isola (b16) 2020
Parmar, Zhang, Zhu (b60) 2021
Tevet, Habib, Shwartz, Berant (b76) 2018
Sattigeri, Hoffman, Chenthamarakshan, Varshney (b68) 2019; 63
Liu, Huang, Yu, Wang, Mallya (b43) 2021
Jahanian, Chai, Isola (b34) 2019
Morozov, Voynov, Babenko (b51) 2020
Preuer, Renz, Unterthiner, Hochreiter, Klambauer (b61) 2018; 58
Frank, Eisenhofer, Schönherr, Fischer, Kolossa, Holz (b25) 2020
Zeng, Lu, Borji (b92) 2017
Brock, Donahue, Simonyan (b11) 2018
Chong, M.J., Forsyth, D., 2020. Effectively unbiased FID and inception score and where to find them. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6070–6079.
Xu, Yuan, Zhang, Wu (b86) 2018
Razavi, Oord, Vinyals (b64) 2019
Wang, S.-Y., Wang, O., Zhang, R., Owens, A., Efros, A.A., 2020a. CNN-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Vol. 7.
Carreira, J., Zisserman, A., 2017. Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6299–6308.
Karras, T., Laine, S., Aila, T., 2019. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4401–4410.
Lucic, Kurach, Michalski, Gelly, Bousquet (b46) 2017
Narvekar, Karam (b53) 2009
Gragnaniello, Cozzolino, Marra, Poggi, Verdoliva (b28) 2021
Bau, Zhu, Strobelt, Zhou, Tenenbaum, Freeman, Torralba (b6) 2018
Wang, Healy, Smeaton, Ward (b83) 2020; 12
Mathiasen, Hvilshøj (b48) 2020
Kynkäänniemi, Karras, Laine, Lehtinen, Aila (b41) 2019
Shmelkov, Schmid, Alahari (b69) 2018
Nash, Menick, Dieleman, Battaglia (b54) 2021
Dzanic, Shah, Witherden (b24) 2019
Alaa, van Breugel, Saveliev, van der Schaar (b1) 2021
Liu, Wei, Lu, Zhou (b45) 2018
Bond-Taylor, Leach, Long, Willcocks (b9) 2021
Kingma, Welling (b39) 2013
Tsitsulin, Munkhoeva, Mottin, Karras, Bronstein, Oseledets, Müller (b79) 2019
Luzi, Marrero, Wynar, Baraniuk, Henry (b47) 2021
Kolchinski, Zhou, Zhao, Gordon, Ermon (b40) 2019
Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D., 2018. Pose guided human video generation. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 201–216.
Jiang, Chang, Wang (b35) 2021
Barannikov, Trofimov, Sotnikov, Trimbach, Korotin, Filippov, Burnaev (b3) 2021
Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b27) 2014
Yu, N., Davis, L.S., Fritz, M., 2019. Attributing fake images to gans: Learning and analyzing gan fingerprints. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 7556–7566.
Xuan, Yang, Yang, He, Wang (b87) 2019
Durall, R., Keuper, M., Keuper, J., 2020. Watch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7890–7899.
Ravuri, Vinyals (b63) 2019
Zhou, Gordon, Krishna, Narcomey, Fei-Fei, Bernstein (b95) 2019
Naeem, Oh, Uh, Choi, Yoo (b52) 2020
De, Masilamani (b19) 2013; 64
Barratt, Sharma (b4) 2018
Bau, D., Zhu, J.-Y., Wulff, J., Peebles, W., Strobelt, H., Zhou, B., Torralba, A., 2019. Seeing what a gan cannot generate. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4502–4511.
van Steenkiste, Kurach, Schmidhuber, Gelly (b75) 2020; 130
Yu, Li, Zhou, Malik, Davis, Fritz (b90) 2020
Zhao, Ren, Yuan, Song, Goodman, Ermon (b94) 2018
Bińkowski, Sutherland, Arbel, Gretton (b8) 2018
Galteri, Seidenari, Bongini, Bertini, Del Bimbo (b26) 2021
Odena (b56) 2019; 4
Barua, Ma, Erfani, Houle, Bailey (b5) 2019
Oprea, Martinez-Gonzalez, Garcia-Garcia, Castro-Vargas, Orts-Escolano, Garcia-Rodriguez, Argyros (b58) 2020
Simon, Webster, Rabin (b72) 2019
Khrulkov, Oseledets (b38) 2018
Gulrajani, Raffel, Metz (b30) 2020
Grnarova, Levy, Lucchi, Perraudin, Goodfellow, Hofmann, Krause (b29) 2019
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8110–8119.
Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C., 2018. Lip movements generation at a glance. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 520–535.
Heusel, Ramsauer, Unterthiner, Nessler, Hochreiter (b31) 2017
Ding, Yang, Hong, Zheng, Zhou, Yin, Lin, Zou, Shao, Yang (b21) 2021
Meehan, Chaudhuri, Dasgupta (b50) 2020
Unterthiner, van Steenkiste, Kurach, Marinier, Michalski, Gelly (b81) 2019
van den Burg, Williams (b13) 2021
O’Brien, Groh, Dubey (b55) 2018
Tolosana, Vera-Rodriguez, Fierrez, Morales, Ortega-Garcia (b78) 2020; 64
Bai, Lin, Raffel, Kan (b2) 2021
Casanova, Drozdzal, Romero-Soriano (b15) 2020
Denton, Chintala, Szlam, Fergus (b20) 2015
Sidheekh, Aimen, Krishnan (b71) 2021
Lee, Town (b42) 2020
Oord, Kalchbrenner, Vinyals, Espeholt, Graves, Kavukcuoglu (b57) 2016
Shoemake, K., 1985. Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques. pp. 245–254.
Borji (b10) 2019; 179
Hudson, Zitnick (b32) 2021
Liu, Z., Luo, P., Wang, X., Tang, X., 2015. Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3730–3738.
Salimans, Goodfellow, Zaremba, Cheung, Radford, Chen (b67) 2016
Soloveitchik, Diskin, Morin, Wiesel (b74) 2021
Nash (10.1016/j.cviu.2021.103329_b54) 2021
Barannikov (10.1016/j.cviu.2021.103329_b3) 2021
Alaa (10.1016/j.cviu.2021.103329_b1) 2021
McDuff (10.1016/j.cviu.2021.103329_b49) 2019
van den Burg (10.1016/j.cviu.2021.103329_b13) 2021
Bond-Taylor (10.1016/j.cviu.2021.103329_b9) 2021
O’Brien (10.1016/j.cviu.2021.103329_b55) 2018
Grnarova (10.1016/j.cviu.2021.103329_b29) 2019
De (10.1016/j.cviu.2021.103329_b19) 2013; 64
Lee (10.1016/j.cviu.2021.103329_b42) 2020
Bai (10.1016/j.cviu.2021.103329_b2) 2021
Liu (10.1016/j.cviu.2021.103329_b45) 2018
10.1016/j.cviu.2021.103329_b80
Sattigeri (10.1016/j.cviu.2021.103329_b68) 2019; 63
Oprea (10.1016/j.cviu.2021.103329_b58) 2020
Bau (10.1016/j.cviu.2021.103329_b6) 2018
Chai (10.1016/j.cviu.2021.103329_b16) 2020
10.1016/j.cviu.2021.103329_b85
Heusel (10.1016/j.cviu.2021.103329_b31) 2017
10.1016/j.cviu.2021.103329_b44
10.1016/j.cviu.2021.103329_b88
Zhao (10.1016/j.cviu.2021.103329_b94) 2018
Barua (10.1016/j.cviu.2021.103329_b5) 2019
10.1016/j.cviu.2021.103329_b89
Buolamwini (10.1016/j.cviu.2021.103329_b12) 2018
Verma (10.1016/j.cviu.2021.103329_b82) 2018
10.1016/j.cviu.2021.103329_b17
Frank (10.1016/j.cviu.2021.103329_b25) 2020
Khrulkov (10.1016/j.cviu.2021.103329_b38) 2018
Brock (10.1016/j.cviu.2021.103329_b11) 2018
10.1016/j.cviu.2021.103329_b18
Salimans (10.1016/j.cviu.2021.103329_b67) 2016
Hudson (10.1016/j.cviu.2021.103329_b32) 2021
Odena (10.1016/j.cviu.2021.103329_b56) 2019; 4
Narvekar (10.1016/j.cviu.2021.103329_b53) 2009
Simonyan (10.1016/j.cviu.2021.103329_b73) 2014
Sajjadi (10.1016/j.cviu.2021.103329_b66) 2018
Gragnaniello (10.1016/j.cviu.2021.103329_b28) 2021
Unterthiner (10.1016/j.cviu.2021.103329_b81) 2019
10.1016/j.cviu.2021.103329_b93
Tevet (10.1016/j.cviu.2021.103329_b76) 2018
10.1016/j.cviu.2021.103329_b7
Morozov (10.1016/j.cviu.2021.103329_b51) 2020
Lucic (10.1016/j.cviu.2021.103329_b46) 2017
10.1016/j.cviu.2021.103329_b59
10.1016/j.cviu.2021.103329_b14
Iqbal (10.1016/j.cviu.2021.103329_b33) 2020
Oord (10.1016/j.cviu.2021.103329_b57) 2016
Tsitsulin (10.1016/j.cviu.2021.103329_b79) 2019
Galteri (10.1016/j.cviu.2021.103329_b26) 2021
Ding (10.1016/j.cviu.2021.103329_b21) 2021
Djolonga (10.1016/j.cviu.2021.103329_b22) 2020
Goodfellow (10.1016/j.cviu.2021.103329_b27) 2014
van Steenkiste (10.1016/j.cviu.2021.103329_b75) 2020; 130
Luzi (10.1016/j.cviu.2021.103329_b47) 2021
Barratt (10.1016/j.cviu.2021.103329_b4) 2018
Shmelkov (10.1016/j.cviu.2021.103329_b69) 2018
Wang (10.1016/j.cviu.2021.103329_b83) 2020; 12
Liu (10.1016/j.cviu.2021.103329_b43) 2021
Parmar (10.1016/j.cviu.2021.103329_b60) 2021
Soloveitchik (10.1016/j.cviu.2021.103329_b74) 2021
Xu (10.1016/j.cviu.2021.103329_b86) 2018
Kingma (10.1016/j.cviu.2021.103329_b39) 2013
Simon (10.1016/j.cviu.2021.103329_b72) 2019
Borji (10.1016/j.cviu.2021.103329_b10) 2019; 179
Kolchinski (10.1016/j.cviu.2021.103329_b40) 2019
Mathiasen (10.1016/j.cviu.2021.103329_b48) 2020
Ramesh (10.1016/j.cviu.2021.103329_b62) 2021
Yu (10.1016/j.cviu.2021.103329_b91) 2015
Kynkäänniemi (10.1016/j.cviu.2021.103329_b41) 2019
10.1016/j.cviu.2021.103329_b23
Jahanian (10.1016/j.cviu.2021.103329_b34) 2019
Razavi (10.1016/j.cviu.2021.103329_b64) 2019
Zeng (10.1016/j.cviu.2021.103329_b92) 2017
Theis (10.1016/j.cviu.2021.103329_b77) 2015
Wang (10.1016/j.cviu.2021.103329_b84) 2019
Naeem (10.1016/j.cviu.2021.103329_b52) 2020
Meehan (10.1016/j.cviu.2021.103329_b50) 2020
Preuer (10.1016/j.cviu.2021.103329_b61) 2018; 58
Roblek (10.1016/j.cviu.2021.103329_b65) 2019
Yu (10.1016/j.cviu.2021.103329_b90) 2020
Zhou (10.1016/j.cviu.2021.103329_b95) 2019
Ravuri (10.1016/j.cviu.2021.103329_b63) 2019
Bińkowski (10.1016/j.cviu.2021.103329_b8) 2018
Denton (10.1016/j.cviu.2021.103329_b20) 2015
Gulrajani (10.1016/j.cviu.2021.103329_b30) 2020
Jiang (10.1016/j.cviu.2021.103329_b35) 2021
10.1016/j.cviu.2021.103329_b70
Dzanic (10.1016/j.cviu.2021.103329_b24) 2019
Casanova (10.1016/j.cviu.2021.103329_b15) 2020
Tolosana (10.1016/j.cviu.2021.103329_b78) 2020; 64
Sidheekh (10.1016/j.cviu.2021.103329_b71) 2021
Xuan (10.1016/j.cviu.2021.103329_b87) 2019
10.1016/j.cviu.2021.103329_b37
10.1016/j.cviu.2021.103329_b36
References_xml – year: 2016
  ident: b57
  article-title: Conditional image generation with pixelcnn decoders
– year: 2021
  ident: b3
  article-title: Manifold topology divergence: a framework for comparing data manifolds
– year: 2020
  ident: b33
  article-title: The survey: Text generation models in deep learning
  publication-title: J. King Saud Univ.-Comput. Inf. Sci.
– volume: 58
  start-page: 1736
  year: 2018
  end-page: 1741
  ident: b61
  article-title: Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery
  publication-title: J. Chem. Inf. Model.
– reference: Wang, S.-Y., Wang, O., Zhang, R., Owens, A., Efros, A.A., 2020a. CNN-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Vol. 7.
– start-page: 12092
  year: 2019
  end-page: 12102
  ident: b29
  article-title: A domain agnostic measure for monitoring and evaluating GANs
  publication-title: Advances in Neural Information Processing Systems
– year: 2021
  ident: b71
  article-title: Characterizing GAN convergence through proximal duality gap
– volume: 64
  start-page: 131
  year: 2020
  end-page: 148
  ident: b78
  article-title: Deepfakes and beyond: A survey of face manipulation and fake detection
  publication-title: Inf. Fusion
– year: 2019
  ident: b64
  article-title: Generating diverse high-fidelity images with vq-vae-2
– year: 2020
  ident: b15
  article-title: Generating unseen complex scenes: are we there yet?
– year: 2021
  ident: b60
  article-title: On buggy resizing libraries and surprising subtleties in FID calculation
– year: 2020
  ident: b50
  article-title: A non-parametric test to detect data-copying in generative models
– reference: Yu, N., Davis, L.S., Fritz, M., 2019. Attributing fake images to gans: Learning and analyzing gan fingerprints. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 7556–7566.
– volume: 64
  start-page: 149
  year: 2013
  end-page: 158
  ident: b19
  article-title: Image sharpness measure for blurred images in frequency domain
  publication-title: Procedia Eng.
– year: 2015
  ident: b91
  article-title: Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop
– year: 2017
  ident: b31
  article-title: Gans trained by a two time-scale update rule converge to a local nash equilibrium
– year: 2017
  ident: b46
  article-title: Are gans created equal? a large-scale study
– year: 2018
  ident: b55
  article-title: Evaluating generative adversarial networks on explicitly parameterized distributions
– year: 2019
  ident: b79
  article-title: The shape of data: Intrinsic distance for data distributions
– start-page: 2550
  year: 2020
  end-page: 2559
  ident: b22
  article-title: Precision-recall curves using information divergence frontiers
  publication-title: International Conference on Artificial Intelligence and Statistics
– reference: Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C., 2018. Lip movements generation at a glance. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 520–535.
– year: 2014
  ident: b73
  article-title: Very deep convolutional networks for large-scale image recognition
– start-page: 3449
  year: 2019
  end-page: 3461
  ident: b95
  article-title: Hype: A benchmark for human eye perceptual evaluation of generative models
  publication-title: Advances in Neural Information Processing Systems
– volume: 179
  start-page: 41
  year: 2019
  end-page: 65
  ident: b10
  article-title: Pros and cons of gan evaluation measures
  publication-title: Comput. Vis. Image Underst.
– reference: Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O., 2018. The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 586–595.
– year: 2021
  ident: b2
  article-title: On training sample memorization: Lessons from Benchmarking generative modeling with a large-scale competition
– year: 2016
  ident: b67
  article-title: Improved techniques for training gans
– volume: 130
  start-page: 309
  year: 2020
  end-page: 325
  ident: b75
  article-title: Investigating object compositionality in generative adversarial networks
  publication-title: Neural Netw.
– year: 2021
  ident: b62
  article-title: Zero-shot text-to-image generation
– reference: Bau, D., Zhu, J.-Y., Wulff, J., Peebles, W., Strobelt, H., Zhou, B., Torralba, A., 2019. Seeing what a gan cannot generate. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4502–4511.
– year: 2021
  ident: b32
  article-title: Generative adversarial transformers
– year: 2020
  ident: b51
  article-title: On self-supervised image representations for GAN evaluation
  publication-title: International Conference on Learning Representations
– year: 2018
  ident: b8
  article-title: Demystifying mmd gans
– year: 2019
  ident: b40
  article-title: Approximating human judgment of generated image quality
– start-page: 5228
  year: 2018
  end-page: 5237
  ident: b66
  article-title: Assessing generative models via precision and recall
  publication-title: Advances in Neural Information Processing Systems
– year: 2019
  ident: b84
  article-title: Generative adversarial networks in computer vision: A survey and taxonomy
– year: 2019
  ident: b34
  article-title: On the”steerability” of generative adversarial networks
– year: 2021
  ident: b47
  article-title: Evaluating generative networks using Gaussian mixtures of image features
– volume: 63
  start-page: 3:1
  year: 2019
  end-page: 3:9
  ident: b68
  article-title: Fairness GAN: Generating datasets with fairness properties using a generative adversarial network
  publication-title: IBM J. Res. Dev.
– year: 2019
  ident: b72
  article-title: Revisiting precision and recall definition for generative model evaluation
– year: 2021
  ident: b13
  article-title: On memorization in probabilistic deep generative models
– year: 2019
  ident: b24
  article-title: Fourier spectrum discrepancies in deep network generated images
– year: 2020
  ident: b58
  article-title: A review on deep learning techniques for video prediction
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– reference: Durall, R., Keuper, M., Keuper, J., 2020. Watch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7890–7899.
– year: 2020
  ident: b48
  article-title: Fast fr
– year: 2021
  ident: b35
  article-title: Transgan: Two transformers can make one strong gan
– volume: 4
  year: 2019
  ident: b56
  article-title: Open questions about generative adversarial networks
  publication-title: Distill
– reference: Yang, C., Wang, Z., Zhu, X., Huang, C., Shi, J., Lin, D., 2018. Pose guided human video generation. In: Proceedings of the European Conference on Computer Vision (ECCV). pp. 201–216.
– start-page: 77
  year: 2018
  end-page: 91
  ident: b12
  article-title: Gender shades: Intersectional accuracy disparities in commercial gender classification
  publication-title: Conference on Fairness, Accountability and Transparency
– year: 2015
  ident: b20
  article-title: Deep generative image models using a laplacian pyramid of adversarial networks
– start-page: 103
  year: 2020
  end-page: 120
  ident: b16
  article-title: What makes fake images detectable? Understanding properties that generalize
  publication-title: European Conference on Computer Vision
– start-page: 377
  year: 2020
  end-page: 393
  ident: b90
  article-title: Inclusive gan: Improving data and minority coverage in generative models
  publication-title: European Conference on Computer Vision
– year: 2019
  ident: b41
  article-title: Improved precision and recall metric for assessing generative models
– year: 2021
  ident: b21
  article-title: CogView: Mastering text-to-image generation via transformers
– start-page: 570
  year: 2018
  end-page: 575
  ident: b86
  article-title: Fairgan: Fairness-aware generative adversarial networks
  publication-title: 2018 IEEE International Conference on Big Data (Big Data)
– reference: Chong, M.J., Forsyth, D., 2020. Effectively unbiased FID and inception score and where to find them. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6070–6079.
– reference: Tulyakov, S., Liu, M.-Y., Yang, X., Kautz, J., 2018. Mocogan: Decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1526–1535.
– year: 2019
  ident: b65
  article-title: Fr
– start-page: 213
  year: 2018
  end-page: 229
  ident: b69
  article-title: How good is my gan?
  publication-title: Proceedings of the European Conference on Computer Vision (ECCV)
– start-page: 3247
  year: 2020
  end-page: 3258
  ident: b25
  article-title: Leveraging frequency analysis for deep fake image recognition
  publication-title: International Conference on Machine Learning
– year: 2018
  ident: b4
  article-title: A note on the inception score
– start-page: 12268
  year: 2019
  end-page: 12279
  ident: b63
  article-title: Classification accuracy score for conditional generative models
  publication-title: Advances in Neural Information Processing Systems
– year: 2021
  ident: b74
  article-title: Conditional frechet inception distance
– year: 2018
  ident: b76
  article-title: Evaluating text gans as language models
– year: 2021
  ident: b43
  article-title: Generative adversarial networks for image and video synthesis: Algorithms and applications
  publication-title: Proc. IEEE
– year: 2021
  ident: b1
  article-title: How faithful is your synthetic data? Sample-level metrics for evaluating and auditing generative models
– year: 2018
  ident: b6
  article-title: Gan dissection: Visualizing and understanding generative adversarial networks
– start-page: 87
  year: 2009
  end-page: 91
  ident: b53
  article-title: A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection
  publication-title: 2009 International Workshop on Quality of Multimedia Experience
– year: 2021
  ident: b54
  article-title: Generating images with sparse representations
– year: 2017
  ident: b92
  article-title: Statistics of deep generated images
– year: 2021
  ident: b28
  article-title: Are GAN generated images easy to detect? A critical analysis of the state-of-the-art
– reference: Park, T., Liu, M.-Y., Wang, T.-C., Zhu, J.-Y., 2019. Semantic image synthesis with spatially-adaptive normalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2337–2346.
– year: 2019
  ident: b5
  article-title: Quality evaluation of gans using cross local intrinsic dimensionality
– year: 2019
  ident: b81
  article-title: FVD: A new metric for video generation
– year: 2020
  ident: b30
  article-title: Towards GAN benchmarks which require generalization
– year: 2018
  ident: b45
  article-title: An improved evaluation framework for generative adversarial networks
– year: 2019
  ident: b87
  article-title: On the anomalous generalization of GANs
– start-page: 2621
  year: 2018
  end-page: 2629
  ident: b38
  article-title: Geometry score: A method for comparing generative adversarial networks
  publication-title: International Conference on Machine Learning
– year: 2020
  ident: b52
  article-title: Reliable fidelity and diversity metrics for generative models
– start-page: 1
  year: 2018
  end-page: 7
  ident: b82
  article-title: Fairness definitions explained
  publication-title: 2018 Ieee/Acm International Workshop on Software Fairness (Fairware)
– reference: Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T., 2020. Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8110–8119.
– year: 2013
  ident: b39
  article-title: Auto-encoding variational bayes
– reference: Shoemake, K., 1985. Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques. pp. 245–254.
– year: 2014
  ident: b27
  article-title: Generative adversarial networks
– year: 2018
  ident: b11
  article-title: Large scale GAN training for high fidelity natural image synthesis
– year: 2021
  ident: b26
  article-title: Language based image quality assessment
– reference: Carreira, J., Zisserman, A., 2017. Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 6299–6308.
– year: 2015
  ident: b77
  article-title: A note on the evaluation of generative models
– year: 2019
  ident: b49
  article-title: Characterizing bias in classifiers using generative models
– reference: Karras, T., Laine, S., Aila, T., 2019. A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4401–4410.
– year: 2020
  ident: b42
  article-title: Mimicry: Towards the reproducibility of GAN research
– volume: 12
  start-page: 13
  year: 2020
  end-page: 24
  ident: b83
  article-title: Use of neural signals to evaluate the quality of generative adversarial network performance in facial image generation
  publication-title: Cogn. Comput.
– reference: Liu, Z., Luo, P., Wang, X., Tang, X., 2015. Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 3730–3738.
– year: 2021
  ident: b9
  article-title: Deep generative modelling: A comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models
– start-page: 10792
  year: 2018
  end-page: 10801
  ident: b94
  article-title: Bias and generalization in deep generative models: An empirical study
  publication-title: Advances in Neural Information Processing Systems
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b28
– volume: 130
  start-page: 309
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b75
  article-title: Investigating object compositionality in generative adversarial networks
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2020.07.007
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b4
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b81
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b11
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b32
– ident: 10.1016/j.cviu.2021.103329_b93
  doi: 10.1109/CVPR.2018.00068
– volume: 58
  start-page: 1736
  issue: 9
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b61
  article-title: Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery
  publication-title: J. Chem. Inf. Model.
  doi: 10.1021/acs.jcim.8b00234
– ident: 10.1016/j.cviu.2021.103329_b88
  doi: 10.1007/978-3-030-01249-6_13
– start-page: 87
  year: 2009
  ident: 10.1016/j.cviu.2021.103329_b53
  article-title: A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection
– year: 2013
  ident: 10.1016/j.cviu.2021.103329_b39
– volume: 64
  start-page: 131
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b78
  article-title: Deepfakes and beyond: A survey of face manipulation and fake detection
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2020.06.014
– year: 2015
  ident: 10.1016/j.cviu.2021.103329_b91
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b60
– year: 2017
  ident: 10.1016/j.cviu.2021.103329_b46
– year: 2015
  ident: 10.1016/j.cviu.2021.103329_b77
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b72
– ident: 10.1016/j.cviu.2021.103329_b17
  doi: 10.1007/978-3-030-01234-2_32
– start-page: 12092
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b29
  article-title: A domain agnostic measure for monitoring and evaluating GANs
– year: 2016
  ident: 10.1016/j.cviu.2021.103329_b57
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b15
– ident: 10.1016/j.cviu.2021.103329_b37
  doi: 10.1109/CVPR42600.2020.00813
– start-page: 5228
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b66
  article-title: Assessing generative models via precision and recall
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b41
– volume: 12
  start-page: 13
  issue: 1
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b83
  article-title: Use of neural signals to evaluate the quality of generative adversarial network performance in facial image generation
  publication-title: Cogn. Comput.
  doi: 10.1007/s12559-019-09670-y
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b51
  article-title: On self-supervised image representations for GAN evaluation
– start-page: 1
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b82
  article-title: Fairness definitions explained
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b87
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b40
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b26
– volume: 64
  start-page: 149
  year: 2013
  ident: 10.1016/j.cviu.2021.103329_b19
  article-title: Image sharpness measure for blurred images in frequency domain
  publication-title: Procedia Eng.
  doi: 10.1016/j.proeng.2013.09.086
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b24
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b47
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b58
  article-title: A review on deep learning techniques for video prediction
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b74
– start-page: 10792
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b94
  article-title: Bias and generalization in deep generative models: An empirical study
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b65
– volume: 63
  start-page: 3:1
  issue: 4/5
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b68
  article-title: Fairness GAN: Generating datasets with fairness properties using a generative adversarial network
  publication-title: IBM J. Res. Dev.
  doi: 10.1147/JRD.2019.2945519
– year: 2017
  ident: 10.1016/j.cviu.2021.103329_b92
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b9
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b50
– year: 2014
  ident: 10.1016/j.cviu.2021.103329_b73
– start-page: 213
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b69
  article-title: How good is my gan?
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b49
– year: 2016
  ident: 10.1016/j.cviu.2021.103329_b67
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b34
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b8
– volume: 4
  issue: 4
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b56
  article-title: Open questions about generative adversarial networks
  publication-title: Distill
  doi: 10.23915/distill.00018
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b52
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b84
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b13
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b30
– ident: 10.1016/j.cviu.2021.103329_b36
  doi: 10.1109/CVPR.2019.00453
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b55
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b71
– year: 2017
  ident: 10.1016/j.cviu.2021.103329_b31
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b62
– ident: 10.1016/j.cviu.2021.103329_b44
  doi: 10.1109/ICCV.2015.425
– volume: 179
  start-page: 41
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b10
  article-title: Pros and cons of gan evaluation measures
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1016/j.cviu.2018.10.009
– start-page: 3449
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b95
  article-title: Hype: A benchmark for human eye perceptual evaluation of generative models
– start-page: 103
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b16
  article-title: What makes fake images detectable? Understanding properties that generalize
– year: 2015
  ident: 10.1016/j.cviu.2021.103329_b20
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b21
– ident: 10.1016/j.cviu.2021.103329_b89
  doi: 10.1109/ICCV.2019.00765
– start-page: 77
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b12
  article-title: Gender shades: Intersectional accuracy disparities in commercial gender classification
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b6
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b54
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b42
– start-page: 2621
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b38
  article-title: Geometry score: A method for comparing generative adversarial networks
– start-page: 2550
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b22
  article-title: Precision-recall curves using information divergence frontiers
– ident: 10.1016/j.cviu.2021.103329_b59
  doi: 10.1109/CVPR.2019.00244
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b64
– start-page: 377
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b90
  article-title: Inclusive gan: Improving data and minority coverage in generative models
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b33
  article-title: The survey: Text generation models in deep learning
  publication-title: J. King Saud Univ.-Comput. Inf. Sci.
– ident: 10.1016/j.cviu.2021.103329_b80
  doi: 10.1109/CVPR.2018.00165
– ident: 10.1016/j.cviu.2021.103329_b85
  doi: 10.1109/CVPR42600.2020.00872
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b79
– year: 2019
  ident: 10.1016/j.cviu.2021.103329_b5
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b35
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b43
  article-title: Generative adversarial networks for image and video synthesis: Algorithms and applications
  publication-title: Proc. IEEE
  doi: 10.1109/JPROC.2021.3049196
– year: 2020
  ident: 10.1016/j.cviu.2021.103329_b48
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b1
– ident: 10.1016/j.cviu.2021.103329_b70
  doi: 10.1145/325334.325242
– start-page: 3247
  year: 2020
  ident: 10.1016/j.cviu.2021.103329_b25
  article-title: Leveraging frequency analysis for deep fake image recognition
– start-page: 570
  year: 2018
  ident: 10.1016/j.cviu.2021.103329_b86
  article-title: Fairgan: Fairness-aware generative adversarial networks
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b76
– ident: 10.1016/j.cviu.2021.103329_b7
  doi: 10.1109/ICCV.2019.00460
– ident: 10.1016/j.cviu.2021.103329_b14
  doi: 10.1109/CVPR.2017.502
– year: 2014
  ident: 10.1016/j.cviu.2021.103329_b27
– year: 2018
  ident: 10.1016/j.cviu.2021.103329_b45
– start-page: 12268
  year: 2019
  ident: 10.1016/j.cviu.2021.103329_b63
  article-title: Classification accuracy score for conditional generative models
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b2
– year: 2021
  ident: 10.1016/j.cviu.2021.103329_b3
– ident: 10.1016/j.cviu.2021.103329_b18
  doi: 10.1109/CVPR42600.2020.00611
– ident: 10.1016/j.cviu.2021.103329_b23
  doi: 10.1109/CVPR42600.2020.00791
SSID ssj0011491
Score 2.7061317
Snippet This work is an update of my previous paper on the same topic published a few years ago (Borji, 2019). With the dramatic progress in generative modeling, a...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 103329
SubjectTerms Deepfakes
GAN evaluation
Generative modeling
Title Pros and cons of GAN evaluation measures: New developments
URI https://dx.doi.org/10.1016/j.cviu.2021.103329
Volume 215
WOSCitedRecordID wos000736276200004&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: 1090-235X
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0011491
  issn: 1077-3142
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtZ3NT9swFMCtQXcYBwZsiI8N-bBbFZTYSe1wqxDbQFPVQzX1FsVfUitIUb_En89z7aSmYwgOXKLKSpyoP-flvef3gdAPKg2NDVFRZnIepaWgERd5J9LcKFgfQuWr3fO_f1ivx4fDvO-7t81W7QRYVfGHh_z-XVHDGMC2qbNvwN1MCgPwG6DDEbDD8VXg-_Dd89lqLsTtV7cXFPVu3zmv4CoUzkY3qnXY0CxUVet-D22Xfu52Ge5siM8iTIhp7PnJdDxyKTOj0JVASOBKcNIvZtZpmT4RjyTJAgGXxJQ6F8U_ste5AcbncjlagOFNkvP1yU8LXW98gJqwwDribFzYOQo7R-Hm2EItwrIcJG-re301vGk2isDAS1xYqXtynxflQvg2n-R53SPQJwZ7aNcbArjrAO6jD7o6QJ-9UYC9yJ3BUM2hHjtAO0ERyS_owgLHAANb4HhiMADHa-C4Bn6BATcOcX9Fg59Xg8vfke-IEUkax3NQJ0QiZRIrlaaGSJLqEkxCqbQy8CoKMH5FqjKecy6EiMuU8Q4jNJOM6VLEmh6i7WpS6SOEQXHrmFKBwibLVJtOScFwJBm3DgGjE3aMkvqvKqSvFm-bltwW_4d0jNrNNfeuVsqLZ2c1gcJre06LK2BBvXDdyZvucoo-rVf6N7Q9ny70d_RRLuej2fTMr6ZHxG1zrw
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=Pros+and+cons+of+GAN+evaluation+measures%3A+New+developments&rft.jtitle=Computer+vision+and+image+understanding&rft.au=Borji%2C+Ali&rft.date=2022-01-01&rft.issn=1077-3142&rft.volume=215&rft.spage=103329&rft_id=info:doi/10.1016%2Fj.cviu.2021.103329&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_cviu_2021_103329
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-3142&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-3142&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-3142&client=summon