Semi-Supervised Adversarial Variational Autoencoder
We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features....
Saved in:
| Published in: | Machine learning and knowledge extraction Vol. 2; no. 3; pp. 361 - 378 |
|---|---|
| Main Author: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
MDPI
01.09.2020
MDPI AG |
| Subjects: | |
| ISSN: | 2504-4990, 2504-4990 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features. The main contributions are threefold. Firstly, our approach perfectly combines the two models, i.e., GAN and VAE, and thus improves the generation and reconstruction performance of the VAE. Secondly, the VAE training is done in two steps, which allows to dissociate the constraints used for the construction of the latent space on the one hand, and those used for the training of the decoder. By using this two-step learning process, our method can be more widely used in applications other than image processing. While training the encoder, the label information is integrated to better structure the latent space in a supervised way. The third contribution is to use the trained encoder for the consistency principle for deep features extracted from the hidden layers. We present experimental results to show that our method gives better performance than the original VAE. The results demonstrate that the adversarial constraints allow the decoder to generate images that are more authentic and realistic than the conventional VAE. |
|---|---|
| AbstractList | We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features. The main contributions are threefold. Firstly, our approach perfectly combines the two models, i.e., GAN and VAE, and thus improves the generation and reconstruction performance of the VAE. Secondly, the VAE training is done in two steps, which allows to dissociate the constraints used for the construction of the latent space on the one hand, and those used for the training of the decoder. By using this two-step learning process, our method can be more widely used in applications other than image processing. While training the encoder, the label information is integrated to better structure the latent space in a supervised way. The third contribution is to use the trained encoder for the consistency principle for deep features extracted from the hidden layers. We present experimental results to show that our method gives better performance than the original VAE. The results demonstrate that the adversarial constraints allow the decoder to generate images that are more authentic and realistic than the conventional VAE. |
| Author | Zemouri, Ryad |
| Author_xml | – sequence: 1 givenname: Ryad orcidid: 0000-0002-3283-9391 surname: Zemouri fullname: Zemouri, Ryad |
| BackLink | https://cnam.hal.science/hal-02931571$$DView record in HAL |
| BookMark | eNptUE1Lw0AUXETBWnvyD_QqEn37nT2GorZQ8FD1umz2Q7emSdmkBf-9aatQxdMMw8y8x1yg07qpPUJXGG4pVXC3Mh-eAAUgcIIGhAPLmFJwesTP0ahtl9BbpGIY2ADRhV_FbLFZ-7SNrXfjwm19ak2Kphq_7qCLTd3zYtM1vraN8-kSnQVTtX70jUP08nD_PJlm86fH2aSYZ5ZK6DImQsAsBMaYFAFT7qUVRMhS5g6IIYoyAc4SFxQXRlKbCy64UxYHluce6BDNDr2uMUu9TnFl0qduTNR7oUlv2qQu2spr71VZlpZTJUsmOFOWWEtK53LnnJe877o-dL2b6lfVtJjrnQb9P5hLvMW9Fx-8NjVtm3zQNnb7HbpkYqUx6N3g-mjwPnPzJ_Nz5D_3F8Y9gj0 |
| CitedBy_id | crossref_primary_10_1109_JBHI_2023_3279493 crossref_primary_10_3390_diagnostics10121055 crossref_primary_10_1007_s11831_025_10355_z crossref_primary_10_1016_j_ymssp_2022_110093 crossref_primary_10_32604_cmc_2022_025550 crossref_primary_10_1007_s10489_024_05358_5 crossref_primary_10_1109_TIA_2023_3281311 crossref_primary_10_1109_TR_2022_3190639 crossref_primary_10_3390_electronics12081857 crossref_primary_10_1016_j_engappai_2023_105859 crossref_primary_10_3389_fbioe_2021_752658 crossref_primary_10_1109_ACCESS_2024_3354724 |
| Cites_doi | 10.1109/CVPR.2017.18 10.1016/j.compind.2019.01.001 10.1109/ACCESS.2019.2962775 10.1016/j.engappai.2019.04.013 10.1016/j.jprocont.2019.01.008 10.1109/CVPR.2016.278 10.1109/CMD.2018.8535718 10.1016/j.neucom.2018.05.024 10.1167/16.12.326 10.1109/TCDS.2018.2883368 10.1109/JSTSP.2019.2913965 10.1109/ICCV.2017.310 10.1109/ACCESS.2019.2939352 10.1109/ACCESS.2019.2940769 10.1016/j.knosys.2018.12.019 10.1109/TASLP.2019.2950099 10.1016/j.compchemeng.2019.106515 10.3390/app9081526 10.1109/LGRS.2017.2766130 10.1016/j.neuroimage.2019.05.039 10.1109/CVPR.2017.632 10.1109/TNNLS.2019.2900734 10.1109/ICCV.2017.244 10.1016/j.cageo.2019.04.006 10.1016/j.ces.2018.02.008 10.1016/j.neunet.2018.04.020 10.1109/ACCESS.2019.2913468 10.1109/ACCESS.2018.2890693 10.1109/5.726791 10.1109/TNSRE.2019.2940046 10.1109/ICCV.2017.304 10.1109/ACCESS.2019.2894764 10.1109/MSP.2017.2765202 10.1016/j.annpat.2019.01.004 10.1109/CVPR.2017.106 10.1109/ACCESS.2018.2848210 10.1016/j.neunet.2019.05.003 10.1016/j.patcog.2018.12.015 10.1109/ACCESS.2018.2890293 10.1109/ACCESS.2019.2944630 10.1109/CVPR.2017.19 10.1016/j.gpb.2018.08.003 10.1109/TSTE.2019.2897688 10.1109/TIFS.2018.2878538 10.1016/j.neucom.2018.07.034 10.1016/j.neucom.2019.03.013 10.1109/TASLP.2019.2917232 |
| ContentType | Journal Article |
| Copyright | Attribution |
| Copyright_xml | – notice: Attribution |
| DBID | AAYXX CITATION 1XC VOOES DOA |
| DOI | 10.3390/make2030020 |
| DatabaseName | CrossRef Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2504-4990 |
| EndPage | 378 |
| ExternalDocumentID | oai_doaj_org_article_ee9bbbc5397b46549c2cc2bdd8ddde75 oai:HAL:hal-02931571v1 10_3390_make2030020 |
| GroupedDBID | AADQD AAFWJ AAYXX AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS CITATION GROUPED_DOAJ MODMG M~E OK1 1XC AFFHD AFKRA ARAPS BENPR BGLVJ CCPQU HCIFZ IAO ICD ITC K7- PHGZM PHGZT PIMPY PQGLB VOOES |
| ID | FETCH-LOGICAL-c370t-46ff14ff44476f135e7c6267b78d02a293460dc2df956a73c86565d9c1f488e03 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 20 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000681745900008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2504-4990 |
| IngestDate | Fri Oct 03 12:41:35 EDT 2025 Sat Nov 29 15:05:16 EST 2025 Thu Oct 16 04:30:37 EDT 2025 Tue Nov 18 22:34:12 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | data generation adversarial learning variational autoencoder deep feature consistent |
| Language | English |
| License | Attribution: http://creativecommons.org/licenses/by |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c370t-46ff14ff44476f135e7c6267b78d02a293460dc2df956a73c86565d9c1f488e03 |
| ORCID | 0000-0002-3283-9391 |
| OpenAccessLink | https://doaj.org/article/ee9bbbc5397b46549c2cc2bdd8ddde75 |
| PageCount | 18 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_ee9bbbc5397b46549c2cc2bdd8ddde75 hal_primary_oai_HAL_hal_02931571v1 crossref_citationtrail_10_3390_make2030020 crossref_primary_10_3390_make2030020 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-09-01 |
| PublicationDateYYYYMMDD | 2020-09-01 |
| PublicationDate_xml | – month: 09 year: 2020 text: 2020-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Machine learning and knowledge extraction |
| PublicationYear | 2020 |
| Publisher | MDPI MDPI AG |
| Publisher_xml | – name: MDPI – name: MDPI AG |
| References | ref_50 Lecun (ref_67) 1998; 86 Zemouri (ref_20) 2020; 8 Huang (ref_23) 2019; 7 Wang (ref_12) 2019; 28 Mao (ref_31) 2019; 7 ref_57 ref_56 Wang (ref_24) 2019; 7 ref_53 ref_52 ref_51 Zhang (ref_4) 2019; 75 Hwang (ref_55) 2019; 7 Creswell (ref_26) 2018; 35 ref_59 Shao (ref_32) 2019; 106 Wang (ref_19) 2018; 16 ref_60 Hou (ref_54) 2019; 341 Agrawal (ref_13) 2019; 13 ref_68 Song (ref_11) 2019; 7 Liu (ref_30) 2018; 315 Alam (ref_34) 2018; 107 ref_65 Wang (ref_7) 2019; 14 ref_64 Deng (ref_16) 2019; 7 ref_63 Xu (ref_10) 2019; 31 ref_62 ref_29 ref_27 Li (ref_22) 2017; 14 ref_71 Lee (ref_3) 2019; 83 Khodayar (ref_15) 2019; 11 ref_70 ref_36 Canchumuni (ref_2) 2019; 128 Bi (ref_18) 2019; 27 ref_35 Yu (ref_58) 2019; 117 Fan (ref_61) 2019; 88 Cheng (ref_25) 2019; 129 ref_39 ref_38 ref_37 Zemouri (ref_66) 2019; 39 Wang (ref_28) 2018; 310 Sun (ref_8) 2018; 6 Na (ref_21) 2018; 181 He (ref_9) 2019; 7 Kameoka (ref_14) 2019; 27 Han (ref_33) 2019; 165 ref_47 ref_46 ref_45 ref_44 ref_43 ref_42 ref_41 ref_40 ref_1 ref_49 ref_48 Teh (ref_69) 2010; Volume 9 Han (ref_17) 2019; 198 ref_5 Yan (ref_6) 2018; 12 |
| References_xml | – ident: ref_51 doi: 10.1109/CVPR.2017.18 – volume: 106 start-page: 85 year: 2019 ident: ref_32 article-title: Generative adversarial networks for data augmentation in machine fault diagnosis publication-title: Comput. Ind. doi: 10.1016/j.compind.2019.01.001 – volume: 8 start-page: 5438 year: 2020 ident: ref_20 article-title: Deep Convolutional Variational Autoencoder as a 2D-Visualization Tool for Partial Discharge Source Classification in Hydrogenerators publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2962775 – volume: 83 start-page: 13 year: 2019 ident: ref_3 article-title: Process monitoring using variational autoencoder for high-dimensional nonlinear processes publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2019.04.013 – ident: ref_49 – ident: ref_5 – volume: 75 start-page: 136 year: 2019 ident: ref_4 article-title: Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring publication-title: J. Process. Control. doi: 10.1016/j.jprocont.2019.01.008 – ident: ref_37 doi: 10.1109/CVPR.2016.278 – ident: ref_68 – ident: ref_29 doi: 10.1109/CMD.2018.8535718 – volume: 310 start-page: 213 year: 2018 ident: ref_28 article-title: An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.024 – ident: ref_56 doi: 10.1167/16.12.326 – ident: ref_39 – ident: ref_42 – ident: ref_1 – ident: ref_71 – volume: 12 start-page: 30 year: 2018 ident: ref_6 article-title: Abnormal Event Detection from Videos using a Two-stream Recurrent Variational Autoencoder publication-title: IEEE Trans. Cogn. Dev. Syst. doi: 10.1109/TCDS.2018.2883368 – volume: 13 start-page: 244 year: 2019 ident: ref_13 article-title: Modulation Filter Learning Using Deep Variational Networks for Robust Speech Recognition publication-title: IEEE J. Sel. Top. Signal Process. doi: 10.1109/JSTSP.2019.2913965 – ident: ref_36 doi: 10.1109/ICCV.2017.310 – volume: 7 start-page: 126582 year: 2019 ident: ref_55 article-title: PuVAE: A Variational Autoencoder to Purify Adversarial Examples publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2939352 – volume: 7 start-page: 139086 year: 2019 ident: ref_23 article-title: Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2940769 – ident: ref_52 – volume: 165 start-page: 474 year: 2019 ident: ref_33 article-title: A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2018.12.019 – ident: ref_48 – volume: 28 start-page: 157 year: 2019 ident: ref_12 article-title: A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural F0 Model for Statistical Parametric Speech Synthesis publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2019.2950099 – volume: 129 start-page: 106515 year: 2019 ident: ref_25 article-title: A novel process monitoring approach based on variational recurrent autoencoder publication-title: Comput. Chem. Eng. doi: 10.1016/j.compchemeng.2019.106515 – ident: ref_27 doi: 10.3390/app9081526 – ident: ref_62 – ident: ref_38 – volume: 14 start-page: 2395 year: 2017 ident: ref_22 article-title: Prediction of Subsurface NMR T2 Distributions in a Shale Petroleum System Using Variational Autoencoder-Based Neural Networks publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2017.2766130 – volume: 198 start-page: 125 year: 2019 ident: ref_17 article-title: Variational autoencoder: An unsupervised model for encoding and decoding fMRI activity in visual cortex publication-title: NeuroImage doi: 10.1016/j.neuroimage.2019.05.039 – ident: ref_59 – ident: ref_45 doi: 10.1109/CVPR.2017.632 – volume: 31 start-page: 295 year: 2019 ident: ref_10 article-title: Semisupervised Text Classification by Variational Autoencoder publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2019.2900734 – ident: ref_53 – ident: ref_35 doi: 10.1109/ICCV.2017.244 – volume: 128 start-page: 87 year: 2019 ident: ref_2 article-title: Towards a robust parameterization for conditioning facies models using deep variational autoencoders and ensemble smoother publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2019.04.006 – volume: 181 start-page: 68 year: 2018 ident: ref_21 article-title: Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks publication-title: Chem. Eng. Sci. doi: 10.1016/j.ces.2018.02.008 – volume: 107 start-page: 12 year: 2018 ident: ref_34 article-title: Novel deep generative simultaneous recurrent model for efficient representation learning publication-title: Neural Netw. doi: 10.1016/j.neunet.2018.04.020 – volume: 7 start-page: 55679 year: 2019 ident: ref_16 article-title: Collaborative Variational Deep Learning for Healthcare Recommendation publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2913468 – volume: 7 start-page: 9515 year: 2019 ident: ref_31 article-title: Imbalanced Fault Diagnosis of Rolling Bearing Based on Generative Adversarial Network: A Comparative Study publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2890693 – ident: ref_47 – volume: 86 start-page: 2278 year: 1998 ident: ref_67 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – ident: ref_40 – volume: 27 start-page: 2025 year: 2019 ident: ref_18 article-title: EEG-Based Adaptive Driver-Vehicle Interface Using Variational Autoencoder and PI-TSVM publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2019.2940046 – ident: ref_41 doi: 10.1109/ICCV.2017.304 – volume: Volume 9 start-page: 509 year: 2010 ident: ref_69 article-title: Inductive Principles for Restricted Boltzmann Machine Learning publication-title: Machine Learning Research, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13–15 May 2010 – ident: ref_63 – volume: 7 start-page: 22554 year: 2019 ident: ref_24 article-title: Systematic Development of a New Variational Autoencoder Model Based on Uncertain Data for Monitoring Nonlinear Processes publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2894764 – ident: ref_44 – volume: 35 start-page: 53 year: 2018 ident: ref_26 article-title: Generative Adversarial Networks: An Overview publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2017.2765202 – volume: 39 start-page: 119 year: 2019 ident: ref_66 article-title: Intelligence artificielle: Quel avenir en anatomie pathologique? publication-title: Ann. Pathol. doi: 10.1016/j.annpat.2019.01.004 – ident: ref_65 doi: 10.1109/CVPR.2017.106 – volume: 6 start-page: 33353 year: 2018 ident: ref_8 article-title: Learning Sparse Representation With Variational Auto-Encoder for Anomaly Detection publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2848210 – volume: 117 start-page: 104 year: 2019 ident: ref_58 article-title: Understanding autoencoders with information theoretic concepts publication-title: Neural Netw. doi: 10.1016/j.neunet.2019.05.003 – volume: 88 start-page: 643 year: 2019 ident: ref_61 article-title: Autoencoder node saliency: Selecting relevant latent representations publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2018.12.015 – volume: 7 start-page: 5707 year: 2019 ident: ref_9 article-title: Collaborative Additional Variational Autoencoder for Top-N Recommender Systems publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2890293 – volume: 7 start-page: 144618 year: 2019 ident: ref_11 article-title: Latent Space Expanded Variational Autoencoder for Sentence Generation publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2944630 – ident: ref_43 doi: 10.1109/CVPR.2017.19 – ident: ref_50 – volume: 16 start-page: 320 year: 2018 ident: ref_19 article-title: VASC: Dimension Reduction and Visualization of Single-cell RNA-seq Data by Deep Variational Autoencoder publication-title: Genom. Proteom. Bioinform. doi: 10.1016/j.gpb.2018.08.003 – ident: ref_46 – volume: 11 start-page: 571 year: 2019 ident: ref_15 article-title: Convolutional Graph Autoencoder: A Generative Deep Neural Network for Probabilistic Spatio-temporal Solar Irradiance Forecasting publication-title: IEEE Trans. Sustain. Energy doi: 10.1109/TSTE.2019.2897688 – volume: 14 start-page: 1390 year: 2019 ident: ref_7 article-title: Generative Neural Networks for Anomaly Detection in Crowded Scenes publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2018.2878538 – ident: ref_64 – volume: 315 start-page: 412 year: 2018 ident: ref_30 article-title: Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.07.034 – ident: ref_70 – ident: ref_60 – volume: 341 start-page: 183 year: 2019 ident: ref_54 article-title: Improving variational autoencoder with deep feature consistent and generative adversarial training publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.03.013 – ident: ref_57 – volume: 27 start-page: 1432 year: 2019 ident: ref_14 article-title: ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2019.2917232 |
| SSID | ssj0002794104 |
| Score | 2.2622466 |
| Snippet | We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead... |
| SourceID | doaj hal crossref |
| SourceType | Open Website Open Access Repository Enrichment Source Index Database |
| StartPage | 361 |
| SubjectTerms | adversarial learning Artificial Intelligence Computer Science data generation deep feature consistent Machine Learning variational autoencoder |
| Title | Semi-Supervised Adversarial Variational Autoencoder |
| URI | https://cnam.hal.science/hal-02931571 https://doaj.org/article/ee9bbbc5397b46549c2cc2bdd8ddde75 |
| Volume | 2 |
| WOSCitedRecordID | wos000681745900008&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: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2504-4990 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002794104 issn: 2504-4990 databaseCode: M~E dateStart: 20190101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NS8MwFA8yPHgRRcX5RZGdhLA2SZvkOGXDgw5hKruV5gun7oOt29G_3Ze0GxMEL15aCGmbvI--90vT30OopVJDeGIMhnS0wEwQjSGrLrDSzFFRZEQlKhSb4P2-GA7l01apL78nrKIHrgTXtlYqpXQKcVN57i-pidZEGSMMeCYP7KUxl1tg6j18TpMMgEb1Qx4FXN8eFx-WgEXHvrL3VggKTP0QWN7WC6khsPQO0H6dEUadaiSHaMdOjhAd2PEID5Yz78oLa6JQOHlReHOJXv2pWsOLOsty6rkojZ0fo5de9_nuHtf1DbCmPC4xy5xLmHOMMZ65hKaWa8AXXHFhYlJAIGZZbDQxDkBMwakWkHylRurEgdvZmJ6gxmQ6sacogstTDqmDTiW8-qQSNhPcZkRoq3imaBPdrKec65r829eg-MwBBHj55FvyaaLWpvOs4rz4vdutl92miyeqDg2gvrxWX_6X-proGiT_4x73nYfct8UgAJhVskrO_uNJ52iPeKwc9oddoEY5X9pLtKtX5WgxvwrmA8fHr-43TvHMPw |
| linkProvider | Directory of Open Access Journals |
| 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=Semi-Supervised+Adversarial+Variational+Autoencoder&rft.jtitle=Machine+learning+and+knowledge+extraction&rft.au=Ryad+Zemouri&rft.date=2020-09-01&rft.pub=MDPI+AG&rft.eissn=2504-4990&rft.volume=2&rft.issue=3&rft.spage=361&rft.epage=378&rft_id=info:doi/10.3390%2Fmake2030020&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_ee9bbbc5397b46549c2cc2bdd8ddde75 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2504-4990&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2504-4990&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2504-4990&client=summon |