DiffuseVAE++: Mitigating training-sampling mismatch based on additional noise for higher fidelity image generation

Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated remarkable results in image generation. However, there exist a mismatch between the training and sampling process in current diffusion models, in addition, the U-Net denoising network based on simple residual blocks cannot predict no...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 633; s. 129814
Hlavní autori: Yang, Xiaobao, Luo, Wei, Ning, Hailong, Zhang, Guorui, Sun, Wei, Ma, Sugang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 07.06.2025
Predmet:
ISSN:0925-2312
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated remarkable results in image generation. However, there exist a mismatch between the training and sampling process in current diffusion models, in addition, the U-Net denoising network based on simple residual blocks cannot predict noise information accurately, which affects the generated quality. To address these limitations, we present a novel image generation method that achieves higher fidelity. First, by additionally adding the standard Gaussian noise in the diffusion forward process, which does not disrupt the forward process, our method alleviates the mismatch. Subsequently, an important efficient denoising network based on U-Net is presented, where our proposed Simple Squeeze-Excitation and Simple GLU, combined with Depthwise Separable Convolution, enhance the ability of the model to predict real noise using the Simplified Nonlinear No Activation (SNNA) block. Furthermore, considering the structural characteristics of the baseline model, we introduce an additional cross-attention mechanism to enable DDPM to focus on VAE stage characteristics. Allowing the model to more accurately capture and learn the noise information. Finally, it is shown after extensive experiments the proposed DiffuseVAE++ obtains significant gains in FID scores, improving from 3.84 to 2.41 on CIFAR-10 and from 3.94 to 2.30 on CelebA-64. In particular, the IS scores on CIFAR-10 reaches 10.10, which is comparable to the current state-of-the-art methods competitively (e.g., U-ViT, StyleGAN2).
AbstractList Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated remarkable results in image generation. However, there exist a mismatch between the training and sampling process in current diffusion models, in addition, the U-Net denoising network based on simple residual blocks cannot predict noise information accurately, which affects the generated quality. To address these limitations, we present a novel image generation method that achieves higher fidelity. First, by additionally adding the standard Gaussian noise in the diffusion forward process, which does not disrupt the forward process, our method alleviates the mismatch. Subsequently, an important efficient denoising network based on U-Net is presented, where our proposed Simple Squeeze-Excitation and Simple GLU, combined with Depthwise Separable Convolution, enhance the ability of the model to predict real noise using the Simplified Nonlinear No Activation (SNNA) block. Furthermore, considering the structural characteristics of the baseline model, we introduce an additional cross-attention mechanism to enable DDPM to focus on VAE stage characteristics. Allowing the model to more accurately capture and learn the noise information. Finally, it is shown after extensive experiments the proposed DiffuseVAE++ obtains significant gains in FID scores, improving from 3.84 to 2.41 on CIFAR-10 and from 3.94 to 2.30 on CelebA-64. In particular, the IS scores on CIFAR-10 reaches 10.10, which is comparable to the current state-of-the-art methods competitively (e.g., U-ViT, StyleGAN2).
ArticleNumber 129814
Author Sun, Wei
Luo, Wei
Yang, Xiaobao
Ma, Sugang
Ning, Hailong
Zhang, Guorui
Author_xml – sequence: 1
  givenname: Xiaobao
  orcidid: 0000-0003-1515-8663
  surname: Yang
  fullname: Yang, Xiaobao
  email: y78h11b09@xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
– sequence: 2
  givenname: Wei
  surname: Luo
  fullname: Luo, Wei
  email: Backwards@stu.xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
– sequence: 3
  givenname: Hailong
  surname: Ning
  fullname: Ning, Hailong
  email: ninghailong@xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
– sequence: 4
  givenname: Guorui
  surname: Zhang
  fullname: Zhang, Guorui
  email: zgr777@stu.xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
– sequence: 5
  givenname: Wei
  surname: Sun
  fullname: Sun, Wei
  email: sunwei@xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
– sequence: 6
  givenname: Sugang
  surname: Ma
  fullname: Ma, Sugang
  email: msg@xupt.edu.cn
  organization: School of Computer Science & Technology, Xi’an University of Posts and Telecommunications, Xi’an, China
BookMark eNp9kEtPwzAQhH0oEm3hH3DwvUqwnac5IFWlPKQiLsDVcu116iqxKztF6r8nUThz2tXOzmj0LdDMeQcI3VGSUkLL-2Pq4Kx8lzLCipQyXtN8huaEsyJhGWXXaBHjkRBaDdochSdrzDnC93q7Wj3gd9vbRvbWNbgP0rphSaLsTu146WzsZK8OeC8jaOwdlloPBu9ki523EbDxAR9sc4CAjdXQ2v6CbScbwA04CHJ8vkFXRrYRbv_mEn09bz83r8nu4-Vts94lihKSJ6ygRlXG8Lqsqxq4KYmsq7IqNCcZJVDxWkHF8n2Z6YxDxk1dwF6asmRZTkBlS5RPuSr4GAMYcQpDl3ARlIiRlTiKiZUYWYmJ1WB7nGwwdPuxEERUFpwCbQOoXmhv_w_4BdwHeY8
Cites_doi 10.1109/ICCV51070.2023.01816
10.1109/CVPR46437.2021.00088
10.1007/978-3-031-73242-3_3
10.1109/CVPR.2018.00745
10.1109/CVPR52688.2022.01117
10.1109/CVPR52729.2023.02171
10.1109/ICCV51070.2023.00387
10.9734/jamcs/2019/v33i330178
10.1109/CVPR52729.2023.01768
10.3389/fpls.2024.1352935
10.1109/CVPR52729.2023.02159
10.1109/CVPR46437.2021.01268
10.1016/j.neucom.2022.01.029
10.1016/j.neucom.2021.01.047
10.1109/ICCV.2019.00461
10.1109/CVPR42600.2020.00813
10.1186/s40537-024-00944-3
10.1109/CVPR52688.2022.01042
10.1109/CVPR.2019.00453
10.3390/s23156727
10.1109/ICCV.2015.425
10.1016/j.neucom.2023.126589
10.1109/CVPR52733.2024.00806
ContentType Journal Article
Copyright 2025 Elsevier B.V.
Copyright_xml – notice: 2025 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.neucom.2025.129814
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
ExternalDocumentID 10_1016_j_neucom_2025_129814
S0925231225004862
GroupedDBID ---
--K
--M
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXLA
AAXUO
AAYFN
ABBOA
ABCQJ
ABFNM
ABJNI
ABMAC
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
AEBSH
AEIPS
AEKER
AENEX
AFJKZ
AFTJW
AFXIZ
AGCQF
AGHFR
AGUBO
AGWIK
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
AOUOD
APXCP
AXJTR
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
KOM
LG9
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SSH
SSN
SSV
SSZ
T5K
ZMT
~G-
29N
9DU
AAQXK
AAYWO
AAYXX
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADNMO
AEUPX
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKYEP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EFLBG
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
R2-
SBC
WUQ
XPP
~HD
ID FETCH-LOGICAL-c1004-251fc7ff986878e9f60a87675d90310e798ce724b63d39e39f85ebaf662340ec3
ISSN 0925-2312
IngestDate Sat Nov 29 06:55:14 EST 2025
Sun May 04 07:42:44 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords Variational autoencoder
Unconditional generation
Diffusion model
Image generation
Generative model
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1004-251fc7ff986878e9f60a87675d90310e798ce724b63d39e39f85ebaf662340ec3
ORCID 0000-0003-1515-8663
ParticipantIDs crossref_primary_10_1016_j_neucom_2025_129814
elsevier_sciencedirect_doi_10_1016_j_neucom_2025_129814
PublicationCentury 2000
PublicationDate 2025-06-07
PublicationDateYYYYMMDD 2025-06-07
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-07
  day: 07
PublicationDecade 2020
PublicationTitle Neurocomputing (Amsterdam)
PublicationYear 2025
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Pandey, Mukherjee, Rai, Kumar (b37) 2022
Franzese, Corallo, Rossi, Heinonen, Filippone, Michiardi (b75) 2024; 36
Z. Xiao, K. Kreis, A. Vahdat, Tackling the Generative Learning Trilemma with Denoising Diffusion GANs, in: International Conference on Learning Representations, 2021.
W. Peebles, S. Xie, Scalable diffusion models with transformers, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 4195–4205.
Wang, Gu, Hu, Gu (b23) 2023; 553
Sønderby, Raiko, Maaløe, Sønderby, Winther (b43) 2016; 29
Ali, El-Hafeez, Mohany (b18) 2019; 33
Ho, Saharia, Chan, Fleet, Norouzi, Salimans (b4) 2022; 23
T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, T. Aila, Analyzing and improving the image quality of stylegan, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8110–8119.
Dhariwal, Nichol (b3) 2021; 34
Van Den Oord, Vinyals (b45) 2017; 30
Kingma, Dhariwal (b9) 2018; 31
Klushyn, Chen, Kurle, Cseke, van der Smagt (b44) 2019; 32
Si, Huang, Jiang, Liu (b52) 2023
F. Bao, S. Nie, K. Xue, Y. Cao, C. Li, H. Su, J. Zhu, All are worth words: A vit backbone for diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22669–22679.
Nichol, Dhariwal (b38) 2021
Hatamizadeh, Song, Liu, Kautz, Vahdat (b33) 2023
M. Bińkowski, D.J. Sutherland, M. Arbel, A. Gretton, Demystifying MMD GANs, in: International Conference on Learning Representations, 2018.
Yuan, Li, Wang, Yang, Lin, Liu, Wang (b51) 2023
Ho, Jain, Abbeel (b2) 2020; 33
T. Karras, S. Laine, T. Aila, A style-based generator architecture for generative adversarial networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401–4410.
Taha, Mostafa, El-Rahman, Abd El-Hafeez (b16) 2023; 13
Higuera, Boots, Mukadam (b56) 2023
Saabia, El-Hafeez, Zaki (b20) 2019
Eman, Mahmoud, Ibrahim, Abd El-Hafeez (b17) 2023; 23
Salimans, Goodfellow, Zaremba, Cheung, Radford, Chen (b67) 2016; 29
D. Kim, C.-H. Lai, W.-H. Liao, N. Murata, Y. Takida, T. Uesaka, Y. He, Y. Mitsufuji, S. Ermon, Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion, in: The Twelfth International Conference on Learning Representations, 2023.
Y. Qin, H. Zheng, J. Yao, M. Zhou, Y. Zhang, Class-balancing diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18434–18443.
Lemons, Langevin (b62) 2002
T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive Growing of GANs for Improved Quality, Stability, and Variation, in: International Conference on Learning Representations, 2018.
H. Chung, D. Ryu, M.T. McCann, M.L. Klasky, J.C. Ye, Solving 3d inverse problems using pre-trained 2d diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22542–22551.
M. Ranzato, S. Chopra, M. Auli, W. Zaremba, Sequence level training with recurrent neural networks, in: 4th International Conference on Learning Representations, ICLR 2016, 2016.
Elmessery, Maklakov, El-Messery, Baranenko, Gutiérrez, Shams, El-Hafeez, Elsayed, Alhag, Moghanm (b42) 2024; 15
Karras, Aittala, Hellsten, Laine, Lehtinen, Aila (b13) 2020; 33
J. Teng, W. Zheng, M. Ding, W. Hong, J. Wangni, Z. Yang, J. Tang, Relay Diffusion: Unifying diffusion process across resolutions for image synthesis, in: The Twelfth International Conference on Learning Representations, 2024.
Zhuoran, Mingyuan, Haiyu, Shuai, Hongsheng (b57) 2021
Karras, Aittala, Hellsten, Laine, Lehtinen, Aila (b71) 2020; 33
P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873–12883.
Kingma, Welling (b8) 2013
Vahdat, Kautz (b11) 2020; 33
R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684–10695.
Mostafa, Mahmoud, Abd El-Hafeez, ElAraby (b10) 2024; 11
Morales, Fuentes (b41) 2024
J. Ho, T. Salimans, Classifier-Free Diffusion Guidance, in: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, 2021.
J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141.
Vahdat, Kreis, Kautz (b46) 2021; 34
C.H. Lin, C.-C. Chang, Y.-S. Chen, D.-C. Juan, W. Wei, H.-T. Chen, Coco-gan: Generation by parts via conditional coordinating, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 4512–4521.
Choi, Kim, Jeong, Gwon, Yoon (b31) 2021; vol. 1
J. Song, C. Meng, S. Ermon, Denoising Diffusion Implicit Models, in: International Conference on Learning Representations, 2020.
An, Zhao, Ma (b15) 2021; 437
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (b39) 2017; 30
A. Hatamizadeh, J. Song, G. Liu, J. Kautz, A. Vahdat, Diffit: Diffusion vision transformers for image generation, in: European Conference on Computer Vision, 2024.
Sohl-Dickstein, Weiss, Maheswaranathan, Ganguli (b1) 2015
Kynkäänniemi, Karras, Laine, Lehtinen, Aila (b69) 2019; 32
Gong, Li, Feng, Wu, Kong (b28) 2022
Kim, Na, Kwon, Lee, Kang, Moon (b74) 2022; 35
Saharia, Chan, Saxena, Li, Whang, Denton, Ghasemipour, Gontijo Lopes, Karagol Ayan, Salimans (b30) 2022; 35
G. Parmar, D. Li, K. Lee, Z. Tu, Dual contradistinctive generative autoencoder, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 823–832.
S. Chen, P. Sun, Y. Song, P. Luo, Diffusiondet: Diffusion model for object detection, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 19830–19843.
A. Lugmayr, M. Danelljan, A. Romero, F. Yu, R. Timofte, L. Van Gool, Repaint: Inpainting using denoising diffusion probabilistic models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11461–11471.
Li, Yang, Chang, Chen, Feng, Xu, Li, Chen (b24) 2022; 479
Z. Liu, P. Luo, X. Wang, X. Tang, Deep learning face attributes in the wild, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3730–3738.
Heusel, Ramsauer, Unterthiner, Nessler, Hochreiter (b66) 2017; 30
T.M. Mahmoud, B.A. Abdel-latef, T. Abd-El-Hafeez, A. Omar, An effective hybrid method for face detection, in: Proceedings of the Fifth International Conference on Intelligent Computing and Information Systems, Cairo, Egypt, 2011.
Ali, El-Hafeez, Mohany (b19) 2019; 2
Han, Pan, Han, Song, Huang (b58) 2023
Van den Oord, Kalchbrenner, Espeholt, Vinyals, Graves (b5) 2016; 29
Goodfellow, Pouget-Abadie, Mirza, Xu, Warde-Farley, Ozair, Courville, Bengio (b6) 2014; 27
R. Zhu, Y. Pan, Y. Li, T. Yao, Z. Sun, T. Mei, C.W. Chen, Sd-dit: Unleashing the power of self-supervised discrimination in diffusion transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 8435–8445.
El-Sayed, Hafeez (b22) 2012
Zhang, Zhao, Lin (b35) 2022; 35
Austin, Johnson, Ho, Tarlow, Van Den Berg (b25) 2021; 34
Lovelace, Kishore, Wan, Shekhtman, Weinberger (b26) 2024; 36
Bengio, Vinyals, Jaitly, Shazeer (b60) 2015; 28
A. Krizhevsky, G. Hinton, et al., Learning Multiple Layers of Features from Tiny Images, Toronto, ON, Canada, 2009.
Higuera (10.1016/j.neucom.2025.129814_b56) 2023
Lemons (10.1016/j.neucom.2025.129814_b62) 2002
Taha (10.1016/j.neucom.2025.129814_b16) 2023; 13
Vahdat (10.1016/j.neucom.2025.129814_b46) 2021; 34
Sønderby (10.1016/j.neucom.2025.129814_b43) 2016; 29
Karras (10.1016/j.neucom.2025.129814_b71) 2020; 33
Kim (10.1016/j.neucom.2025.129814_b74) 2022; 35
Vaswani (10.1016/j.neucom.2025.129814_b39) 2017; 30
Zhang (10.1016/j.neucom.2025.129814_b35) 2022; 35
10.1016/j.neucom.2025.129814_b7
10.1016/j.neucom.2025.129814_b36
Kingma (10.1016/j.neucom.2025.129814_b8) 2013
10.1016/j.neucom.2025.129814_b34
Ali (10.1016/j.neucom.2025.129814_b19) 2019; 2
10.1016/j.neucom.2025.129814_b72
Goodfellow (10.1016/j.neucom.2025.129814_b6) 2014; 27
10.1016/j.neucom.2025.129814_b70
10.1016/j.neucom.2025.129814_b32
Si (10.1016/j.neucom.2025.129814_b52) 2023
10.1016/j.neucom.2025.129814_b76
Van den Oord (10.1016/j.neucom.2025.129814_b5) 2016; 29
10.1016/j.neucom.2025.129814_b73
Dhariwal (10.1016/j.neucom.2025.129814_b3) 2021; 34
El-Sayed (10.1016/j.neucom.2025.129814_b22) 2012
Van Den Oord (10.1016/j.neucom.2025.129814_b45) 2017; 30
Yuan (10.1016/j.neucom.2025.129814_b51) 2023
10.1016/j.neucom.2025.129814_b47
Saharia (10.1016/j.neucom.2025.129814_b30) 2022; 35
Elmessery (10.1016/j.neucom.2025.129814_b42) 2024; 15
Karras (10.1016/j.neucom.2025.129814_b13) 2020; 33
10.1016/j.neucom.2025.129814_b49
10.1016/j.neucom.2025.129814_b48
Lovelace (10.1016/j.neucom.2025.129814_b26) 2024; 36
Choi (10.1016/j.neucom.2025.129814_b31) 2021; vol. 1
Wang (10.1016/j.neucom.2025.129814_b23) 2023; 553
Nichol (10.1016/j.neucom.2025.129814_b38) 2021
10.1016/j.neucom.2025.129814_b40
Saabia (10.1016/j.neucom.2025.129814_b20) 2019
Austin (10.1016/j.neucom.2025.129814_b25) 2021; 34
Vahdat (10.1016/j.neucom.2025.129814_b11) 2020; 33
Franzese (10.1016/j.neucom.2025.129814_b75) 2024; 36
Mostafa (10.1016/j.neucom.2025.129814_b10) 2024; 11
10.1016/j.neucom.2025.129814_b14
Ho (10.1016/j.neucom.2025.129814_b2) 2020; 33
Kingma (10.1016/j.neucom.2025.129814_b9) 2018; 31
10.1016/j.neucom.2025.129814_b12
Zhuoran (10.1016/j.neucom.2025.129814_b57) 2021
10.1016/j.neucom.2025.129814_b55
10.1016/j.neucom.2025.129814_b59
10.1016/j.neucom.2025.129814_b50
10.1016/j.neucom.2025.129814_b54
10.1016/j.neucom.2025.129814_b53
Ho (10.1016/j.neucom.2025.129814_b4) 2022; 23
Ali (10.1016/j.neucom.2025.129814_b18) 2019; 33
Han (10.1016/j.neucom.2025.129814_b58) 2023
Eman (10.1016/j.neucom.2025.129814_b17) 2023; 23
Pandey (10.1016/j.neucom.2025.129814_b37) 2022
Bengio (10.1016/j.neucom.2025.129814_b60) 2015; 28
Li (10.1016/j.neucom.2025.129814_b24) 2022; 479
Kynkäänniemi (10.1016/j.neucom.2025.129814_b69) 2019; 32
An (10.1016/j.neucom.2025.129814_b15) 2021; 437
Gong (10.1016/j.neucom.2025.129814_b28) 2022
10.1016/j.neucom.2025.129814_b68
10.1016/j.neucom.2025.129814_b29
Klushyn (10.1016/j.neucom.2025.129814_b44) 2019; 32
10.1016/j.neucom.2025.129814_b27
Sohl-Dickstein (10.1016/j.neucom.2025.129814_b1) 2015
10.1016/j.neucom.2025.129814_b61
Morales (10.1016/j.neucom.2025.129814_b41) 2024
10.1016/j.neucom.2025.129814_b21
10.1016/j.neucom.2025.129814_b65
10.1016/j.neucom.2025.129814_b64
Salimans (10.1016/j.neucom.2025.129814_b67) 2016; 29
10.1016/j.neucom.2025.129814_b63
Hatamizadeh (10.1016/j.neucom.2025.129814_b33) 2023
Heusel (10.1016/j.neucom.2025.129814_b66) 2017; 30
References_xml – volume: 11
  start-page: 88
  year: 2024
  ident: b10
  article-title: Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms
  publication-title: J. Big Data
– volume: 29
  year: 2016
  ident: b43
  article-title: Ladder variational autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: P. Esser, R. Rombach, B. Ommer, Taming transformers for high-resolution image synthesis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 12873–12883.
– reference: J. Song, C. Meng, S. Ermon, Denoising Diffusion Implicit Models, in: International Conference on Learning Representations, 2020.
– volume: 35
  start-page: 32270
  year: 2022
  end-page: 32284
  ident: b74
  article-title: Maximum likelihood training of implicit nonlinear diffusion model
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: b33
  article-title: Diffit: Diffusion vision transformers for image generation
– reference: T. Karras, S. Laine, T. Aila, A style-based generator architecture for generative adversarial networks, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 4401–4410.
– volume: 28
  year: 2015
  ident: b60
  article-title: Scheduled sampling for sequence prediction with recurrent neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 30
  year: 2017
  ident: b66
  article-title: Gans trained by a two time-scale update rule converge to a local nash equilibrium
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: G. Parmar, D. Li, K. Lee, Z. Tu, Dual contradistinctive generative autoencoder, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 823–832.
– volume: 34
  start-page: 17981
  year: 2021
  end-page: 17993
  ident: b25
  article-title: Structured denoising diffusion models in discrete state-spaces
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 35
  start-page: 36479
  year: 2022
  end-page: 36494
  ident: b30
  article-title: Photorealistic text-to-image diffusion models with deep language understanding
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, T. Aila, Analyzing and improving the image quality of stylegan, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8110–8119.
– year: 2002
  ident: b62
  article-title: An Introduction to Stochastic Processes in Physics
– volume: 36
  year: 2024
  ident: b75
  article-title: Continuous-time functional diffusion processes
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 437
  start-page: 274
  year: 2021
  end-page: 281
  ident: b15
  article-title: GSA-GAN: Global spatial attention generative adversarial networks
  publication-title: Neurocomputing
– reference: A. Hatamizadeh, J. Song, G. Liu, J. Kautz, A. Vahdat, Diffit: Diffusion vision transformers for image generation, in: European Conference on Computer Vision, 2024.
– volume: 13
  start-page: 25
  year: 2023
  end-page: 35
  ident: b16
  article-title: A novel hybrid approach to masked face recognition using robust PCA and GOA optimizer
  publication-title: Sci. J. Damietta Fac. Sci.
– volume: 29
  year: 2016
  ident: b67
  article-title: Improved techniques for training gans
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 33
  start-page: 12104
  year: 2020
  end-page: 12114
  ident: b13
  article-title: Training generative adversarial networks with limited data
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2012
  ident: b22
  article-title: New edge detection technique based on the shannon entropy in gray level images
– volume: 33
  start-page: 19667
  year: 2020
  end-page: 19679
  ident: b11
  article-title: NVAE: A deep hierarchical variational autoencoder
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: D. Kim, C.-H. Lai, W.-H. Liao, N. Murata, Y. Takida, T. Uesaka, Y. He, Y. Mitsufuji, S. Ermon, Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion, in: The Twelfth International Conference on Learning Representations, 2023.
– year: 2023
  ident: b56
  article-title: Learning to read braille: Bridging the tactile reality gap with diffusion models
– volume: 32
  year: 2019
  ident: b69
  article-title: Improved precision and recall metric for assessing generative models
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: J. Teng, W. Zheng, M. Ding, W. Hong, J. Wangni, Z. Yang, J. Tang, Relay Diffusion: Unifying diffusion process across resolutions for image synthesis, in: The Twelfth International Conference on Learning Representations, 2024.
– reference: T.M. Mahmoud, B.A. Abdel-latef, T. Abd-El-Hafeez, A. Omar, An effective hybrid method for face detection, in: Proceedings of the Fifth International Conference on Intelligent Computing and Information Systems, Cairo, Egypt, 2011.
– volume: 30
  year: 2017
  ident: b45
  article-title: Neural discrete representation learning
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: J. Ho, T. Salimans, Classifier-Free Diffusion Guidance, in: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications, 2021.
– volume: 30
  year: 2017
  ident: b39
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: b51
  article-title: Spatial-frequency U-net for denoising diffusion probabilistic models
– volume: 33
  start-page: 1
  year: 2019
  end-page: 19
  ident: b18
  article-title: An accurate system for face detection and recognition
  publication-title: J. Adv. Math. Comput. Sci.
– volume: 36
  year: 2024
  ident: b26
  article-title: Latent diffusion for language generation
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 35
  start-page: 22117
  year: 2022
  end-page: 22130
  ident: b35
  article-title: Unsupervised representation learning from pre-trained diffusion probabilistic models
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: b52
  article-title: Freeu: Free lunch in diffusion u-net
– volume: 23
  start-page: 6727
  year: 2023
  ident: b17
  article-title: Innovative hybrid approach for masked face recognition using pretrained mask detection and segmentation, robust PCA, and KNN classifier
  publication-title: Sensors
– volume: 29
  year: 2016
  ident: b5
  article-title: Conditional image generation with pixelcnn decoders
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: S. Chen, P. Sun, Y. Song, P. Luo, Diffusiondet: Diffusion model for object detection, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 19830–19843.
– volume: 32
  year: 2019
  ident: b44
  article-title: Learning hierarchical priors in vaes
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: W. Peebles, S. Xie, Scalable diffusion models with transformers, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 4195–4205.
– start-page: 273
  year: 2019
  end-page: 283
  ident: b20
  article-title: Face recognition based on grey wolf optimization for feature selection
  publication-title: Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2018 4
– volume: 33
  start-page: 6840
  year: 2020
  end-page: 6851
  ident: b2
  article-title: Denoising diffusion probabilistic models
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: vol. 1
  start-page: 2
  year: 2021
  ident: b31
  article-title: Ilvr: Conditioning method for denoising diffusion probabilistic models. in 2021 IEEE
  publication-title: CVF International Conference on Computer Vision
– reference: H. Chung, D. Ryu, M.T. McCann, M.L. Klasky, J.C. Ye, Solving 3d inverse problems using pre-trained 2d diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22542–22551.
– start-page: 2256
  year: 2015
  end-page: 2265
  ident: b1
  article-title: Deep unsupervised learning using nonequilibrium thermodynamics
  publication-title: International Conference on Machine Learning
– reference: Y. Qin, H. Zheng, J. Yao, M. Zhou, Y. Zhang, Class-balancing diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18434–18443.
– volume: 479
  start-page: 47
  year: 2022
  end-page: 59
  ident: b24
  article-title: Srdiff: Single image super-resolution with diffusion probabilistic models
  publication-title: Neurocomputing
– start-page: 8162
  year: 2021
  end-page: 8171
  ident: b38
  article-title: Improved denoising diffusion probabilistic models
  publication-title: International Conference on Machine Learning
– reference: A. Lugmayr, M. Danelljan, A. Romero, F. Yu, R. Timofte, L. Van Gool, Repaint: Inpainting using denoising diffusion probabilistic models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11461–11471.
– start-page: 5938
  year: 2023
  end-page: 5948
  ident: b58
  article-title: Flatten transformer: Vision transformer using focused linear attention
  publication-title: 2023 IEEE/CVF International Conference on Computer Vision
– reference: M. Bińkowski, D.J. Sutherland, M. Arbel, A. Gretton, Demystifying MMD GANs, in: International Conference on Learning Representations, 2018.
– volume: 34
  start-page: 11287
  year: 2021
  end-page: 11302
  ident: b46
  article-title: Score-based generative modeling in latent space
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: C.H. Lin, C.-C. Chang, Y.-S. Chen, D.-C. Juan, W. Wei, H.-T. Chen, Coco-gan: Generation by parts via conditional coordinating, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 4512–4521.
– volume: 23
  start-page: 1
  year: 2022
  end-page: 33
  ident: b4
  article-title: Cascaded diffusion models for high fidelity image generation
  publication-title: J. Mach. Learn. Res.
– volume: 553
  year: 2023
  ident: b23
  article-title: Ensemble anomaly score for video anomaly detection using denoise diffusion model and motion filters
  publication-title: Neurocomputing
– reference: J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132–7141.
– volume: 33
  start-page: 12104
  year: 2020
  end-page: 12114
  ident: b71
  article-title: Training generative adversarial networks with limited data
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: A. Krizhevsky, G. Hinton, et al., Learning Multiple Layers of Features from Tiny Images, Toronto, ON, Canada, 2009.
– volume: 34
  start-page: 8780
  year: 2021
  end-page: 8794
  ident: b3
  article-title: Diffusion models beat gans on image synthesis
  publication-title: Adv. Neural Inf. Process. Syst.
– reference: Z. Xiao, K. Kreis, A. Vahdat, Tackling the Generative Learning Trilemma with Denoising Diffusion GANs, in: International Conference on Learning Representations, 2021.
– start-page: 3530
  year: 2021
  end-page: 3538
  ident: b57
  article-title: Efficient attention: Attention with linear complexities
  publication-title: 2021 IEEE Winter Conference on Applications of Computer Vision
– reference: R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684–10695.
– reference: Z. Liu, P. Luo, X. Wang, X. Tang, Deep learning face attributes in the wild, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 3730–3738.
– year: 2013
  ident: b8
  article-title: Auto-encoding variational bayes
– volume: 31
  year: 2018
  ident: b9
  article-title: Glow: Generative flow with invertible 1x1 convolutions
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2024
  ident: b41
  article-title: Efficient generative adversarial networks using linear additive-attention transformers
– volume: 2
  start-page: 1
  year: 2019
  end-page: 12
  ident: b19
  article-title: A robust and efficient system to detect human faces based on facial features
  publication-title: Asian J. Res. Comput. Sci.
– volume: 15
  year: 2024
  ident: b42
  article-title: Semantic segmentation of microbial alterations based on SegFormer
  publication-title: Front. Plant Sci.
– reference: R. Zhu, Y. Pan, Y. Li, T. Yao, Z. Sun, T. Mei, C.W. Chen, Sd-dit: Unleashing the power of self-supervised discrimination in diffusion transformer, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 8435–8445.
– year: 2022
  ident: b28
  article-title: Diffuseq: Sequence to sequence text generation with diffusion models
– reference: M. Ranzato, S. Chopra, M. Auli, W. Zaremba, Sequence level training with recurrent neural networks, in: 4th International Conference on Learning Representations, ICLR 2016, 2016.
– reference: F. Bao, S. Nie, K. Xue, Y. Cao, C. Li, H. Su, J. Zhu, All are worth words: A vit backbone for diffusion models, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 22669–22679.
– year: 2022
  ident: b37
  article-title: Diffusevae: Efficient, controllable and high-fidelity generation from low-dimensional latents
– reference: T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive Growing of GANs for Improved Quality, Stability, and Variation, in: International Conference on Learning Representations, 2018.
– volume: 27
  year: 2014
  ident: b6
  article-title: Generative adversarial nets
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b27
  doi: 10.1109/ICCV51070.2023.01816
– ident: 10.1016/j.neucom.2025.129814_b47
  doi: 10.1109/CVPR46437.2021.00088
– volume: 33
  start-page: 12104
  year: 2020
  ident: 10.1016/j.neucom.2025.129814_b13
  article-title: Training generative adversarial networks with limited data
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 30
  year: 2017
  ident: 10.1016/j.neucom.2025.129814_b45
  article-title: Neural discrete representation learning
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b68
– volume: 29
  year: 2016
  ident: 10.1016/j.neucom.2025.129814_b67
  article-title: Improved techniques for training gans
  publication-title: Adv. Neural Inf. Process. Syst.
– start-page: 5938
  year: 2023
  ident: 10.1016/j.neucom.2025.129814_b58
  article-title: Flatten transformer: Vision transformer using focused linear attention
– ident: 10.1016/j.neucom.2025.129814_b59
  doi: 10.1007/978-3-031-73242-3_3
– year: 2012
  ident: 10.1016/j.neucom.2025.129814_b22
– ident: 10.1016/j.neucom.2025.129814_b49
– ident: 10.1016/j.neucom.2025.129814_b40
  doi: 10.1109/CVPR.2018.00745
– volume: 33
  start-page: 12104
  year: 2020
  ident: 10.1016/j.neucom.2025.129814_b71
  article-title: Training generative adversarial networks with limited data
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b34
  doi: 10.1109/CVPR52688.2022.01117
– volume: 29
  year: 2016
  ident: 10.1016/j.neucom.2025.129814_b43
  article-title: Ladder variational autoencoders
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b53
  doi: 10.1109/CVPR52729.2023.02171
– volume: 29
  year: 2016
  ident: 10.1016/j.neucom.2025.129814_b5
  article-title: Conditional image generation with pixelcnn decoders
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: vol. 1
  start-page: 2
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b31
  article-title: Ilvr: Conditioning method for denoising diffusion probabilistic models. in 2021 IEEE
– start-page: 273
  year: 2019
  ident: 10.1016/j.neucom.2025.129814_b20
  article-title: Face recognition based on grey wolf optimization for feature selection
– year: 2024
  ident: 10.1016/j.neucom.2025.129814_b41
– volume: 36
  year: 2024
  ident: 10.1016/j.neucom.2025.129814_b75
  article-title: Continuous-time functional diffusion processes
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 33
  start-page: 6840
  year: 2020
  ident: 10.1016/j.neucom.2025.129814_b2
  article-title: Denoising diffusion probabilistic models
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: 10.1016/j.neucom.2025.129814_b52
– volume: 32
  year: 2019
  ident: 10.1016/j.neucom.2025.129814_b44
  article-title: Learning hierarchical priors in vaes
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b63
– volume: 34
  start-page: 17981
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b25
  article-title: Structured denoising diffusion models in discrete state-spaces
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 34
  start-page: 11287
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b46
  article-title: Score-based generative modeling in latent space
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b32
– year: 2023
  ident: 10.1016/j.neucom.2025.129814_b33
– ident: 10.1016/j.neucom.2025.129814_b55
  doi: 10.1109/ICCV51070.2023.00387
– volume: 27
  year: 2014
  ident: 10.1016/j.neucom.2025.129814_b6
  article-title: Generative adversarial nets
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 30
  year: 2017
  ident: 10.1016/j.neucom.2025.129814_b66
  article-title: Gans trained by a two time-scale update rule converge to a local nash equilibrium
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 33
  start-page: 1
  issue: 3
  year: 2019
  ident: 10.1016/j.neucom.2025.129814_b18
  article-title: An accurate system for face detection and recognition
  publication-title: J. Adv. Math. Comput. Sci.
  doi: 10.9734/jamcs/2019/v33i330178
– year: 2023
  ident: 10.1016/j.neucom.2025.129814_b51
– start-page: 2256
  year: 2015
  ident: 10.1016/j.neucom.2025.129814_b1
  article-title: Deep unsupervised learning using nonequilibrium thermodynamics
– volume: 33
  start-page: 19667
  year: 2020
  ident: 10.1016/j.neucom.2025.129814_b11
  article-title: NVAE: A deep hierarchical variational autoencoder
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b70
  doi: 10.1109/CVPR52729.2023.01768
– volume: 15
  year: 2024
  ident: 10.1016/j.neucom.2025.129814_b42
  article-title: Semantic segmentation of microbial alterations based on SegFormer
  publication-title: Front. Plant Sci.
  doi: 10.3389/fpls.2024.1352935
– ident: 10.1016/j.neucom.2025.129814_b73
– ident: 10.1016/j.neucom.2025.129814_b21
– ident: 10.1016/j.neucom.2025.129814_b36
  doi: 10.1109/CVPR52729.2023.02159
– volume: 35
  start-page: 22117
  year: 2022
  ident: 10.1016/j.neucom.2025.129814_b35
  article-title: Unsupervised representation learning from pre-trained diffusion probabilistic models
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: 10.1016/j.neucom.2025.129814_b28
– start-page: 3530
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b57
  article-title: Efficient attention: Attention with linear complexities
– volume: 31
  year: 2018
  ident: 10.1016/j.neucom.2025.129814_b9
  article-title: Glow: Generative flow with invertible 1x1 convolutions
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2022
  ident: 10.1016/j.neucom.2025.129814_b37
– start-page: 8162
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b38
  article-title: Improved denoising diffusion probabilistic models
– volume: 35
  start-page: 32270
  year: 2022
  ident: 10.1016/j.neucom.2025.129814_b74
  article-title: Maximum likelihood training of implicit nonlinear diffusion model
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b72
  doi: 10.1109/CVPR46437.2021.01268
– volume: 479
  start-page: 47
  year: 2022
  ident: 10.1016/j.neucom.2025.129814_b24
  article-title: Srdiff: Single image super-resolution with diffusion probabilistic models
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2022.01.029
– volume: 437
  start-page: 274
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b15
  article-title: GSA-GAN: Global spatial attention generative adversarial networks
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.01.047
– volume: 28
  year: 2015
  ident: 10.1016/j.neucom.2025.129814_b60
  article-title: Scheduled sampling for sequence prediction with recurrent neural networks
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 35
  start-page: 36479
  year: 2022
  ident: 10.1016/j.neucom.2025.129814_b30
  article-title: Photorealistic text-to-image diffusion models with deep language understanding
  publication-title: Adv. Neural Inf. Process. Syst.
– year: 2023
  ident: 10.1016/j.neucom.2025.129814_b56
– ident: 10.1016/j.neucom.2025.129814_b76
  doi: 10.1109/ICCV.2019.00461
– volume: 34
  start-page: 8780
  year: 2021
  ident: 10.1016/j.neucom.2025.129814_b3
  article-title: Diffusion models beat gans on image synthesis
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 32
  year: 2019
  ident: 10.1016/j.neucom.2025.129814_b69
  article-title: Improved precision and recall metric for assessing generative models
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b14
  doi: 10.1109/CVPR42600.2020.00813
– year: 2013
  ident: 10.1016/j.neucom.2025.129814_b8
– volume: 11
  start-page: 88
  issue: 1
  year: 2024
  ident: 10.1016/j.neucom.2025.129814_b10
  article-title: Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms
  publication-title: J. Big Data
  doi: 10.1186/s40537-024-00944-3
– ident: 10.1016/j.neucom.2025.129814_b29
  doi: 10.1109/CVPR52688.2022.01042
– ident: 10.1016/j.neucom.2025.129814_b61
– volume: 13
  start-page: 25
  issue: 3
  year: 2023
  ident: 10.1016/j.neucom.2025.129814_b16
  article-title: A novel hybrid approach to masked face recognition using robust PCA and GOA optimizer
  publication-title: Sci. J. Damietta Fac. Sci.
– year: 2002
  ident: 10.1016/j.neucom.2025.129814_b62
– volume: 23
  start-page: 1
  issue: 47
  year: 2022
  ident: 10.1016/j.neucom.2025.129814_b4
  article-title: Cascaded diffusion models for high fidelity image generation
  publication-title: J. Mach. Learn. Res.
– ident: 10.1016/j.neucom.2025.129814_b65
– ident: 10.1016/j.neucom.2025.129814_b12
  doi: 10.1109/CVPR.2019.00453
– volume: 2
  start-page: 1
  issue: 4
  year: 2019
  ident: 10.1016/j.neucom.2025.129814_b19
  article-title: A robust and efficient system to detect human faces based on facial features
  publication-title: Asian J. Res. Comput. Sci.
– ident: 10.1016/j.neucom.2025.129814_b7
– volume: 36
  year: 2024
  ident: 10.1016/j.neucom.2025.129814_b26
  article-title: Latent diffusion for language generation
  publication-title: Adv. Neural Inf. Process. Syst.
– ident: 10.1016/j.neucom.2025.129814_b48
– ident: 10.1016/j.neucom.2025.129814_b50
– volume: 30
  year: 2017
  ident: 10.1016/j.neucom.2025.129814_b39
  article-title: Attention is all you need
  publication-title: Adv. Neural Inf. Process. Syst.
– volume: 23
  start-page: 6727
  issue: 15
  year: 2023
  ident: 10.1016/j.neucom.2025.129814_b17
  article-title: Innovative hybrid approach for masked face recognition using pretrained mask detection and segmentation, robust PCA, and KNN classifier
  publication-title: Sensors
  doi: 10.3390/s23156727
– ident: 10.1016/j.neucom.2025.129814_b64
  doi: 10.1109/ICCV.2015.425
– volume: 553
  year: 2023
  ident: 10.1016/j.neucom.2025.129814_b23
  article-title: Ensemble anomaly score for video anomaly detection using denoise diffusion model and motion filters
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2023.126589
– ident: 10.1016/j.neucom.2025.129814_b54
  doi: 10.1109/CVPR52733.2024.00806
SSID ssj0017129
Score 2.444062
Snippet Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated remarkable results in image generation. However, there exist a mismatch between the training...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 129814
SubjectTerms Diffusion model
Generative model
Image generation
Unconditional generation
Variational autoencoder
Title DiffuseVAE++: Mitigating training-sampling mismatch based on additional noise for higher fidelity image generation
URI https://dx.doi.org/10.1016/j.neucom.2025.129814
Volume 633
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  issn: 0925-2312
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0017129
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMX3ojykg9wWqVK7SS2uS2wUJCoOBRYTlHi2NSrNql2m6p_hX_L-JFHWVTRA9IqWlleJ8p8O_48Hn-D0EtewqJAFzqSqeSwQMngLyWVjuIyqYgiBSFl4opNsIMDvliIL5PJr-4szPkxq2t-cSFO_6upoQ2MbY_OXsPc_aDQAN_B6HAFs8P1nwz_zmjdrtW32fwVeWM_sOb_bLyUxqgmRLQubDI5tIClgbbKo6md0Sq7e2CTjEKMsG7M2uuCH_mMEG11sSx1Nyc23eenk63urbvsxKBamBhdwYgQipidWEWGysKvDz38CLHqhSnAqzR9blDrwrfflRk2TXzH_cIcN2GqHQe7P7TNqjXjAAZJXaIVG0cioQ1o5iWnnFE6cqtASrg_a7rh8X3wYblbq9am_9gb7A7dLwts_zHx9emIXabbMvej5HaU3I9yA20TlgpwmNuzj_PFp36Liu0RL-QYnr47l-mSBzef5u-8Z8RlDu-i22ERgmcePPfQRNX30Z2uwAcO_v4BWg1Ymk5f4wFFeANFuEMRdijCTY0HFGGHIgwowh5FuEMRdijCA4oeoq_v54dv96NQpCOSVmwwAn6sJdNa8IwzroTO4oJbhaBKWNVZxQSXipGkzGhFhaJC81SVhc6AdyexkvQR2qqbWj1GuKSxlsCIU-iQaCXKKqWsYjTRe3GVcrWDou4V5qdeiyW_ynQ7iHXvOQ980vPEHMBz5S-fXPNOT9GtAdnP0NbZqlXP0U15fmbWqxcBOb8BySSauA
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=DiffuseVAE%2B%2B%3A+Mitigating+training-sampling+mismatch+based+on+additional+noise+for+higher+fidelity+image+generation&rft.jtitle=Neurocomputing+%28Amsterdam%29&rft.au=Yang%2C+Xiaobao&rft.au=Luo%2C+Wei&rft.au=Ning%2C+Hailong&rft.au=Zhang%2C+Guorui&rft.date=2025-06-07&rft.issn=0925-2312&rft.volume=633&rft.spage=129814&rft_id=info:doi/10.1016%2Fj.neucom.2025.129814&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neucom_2025_129814
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0925-2312&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0925-2312&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0925-2312&client=summon