{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:03:12Z","timestamp":1774418592483,"version":"3.50.1"},"reference-count":71,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2020,9,6]],"date-time":"2020-09-06T00:00:00Z","timestamp":1599350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/make2030020","type":"journal-article","created":{"date-parts":[[2020,9,6]],"date-time":"2020-09-06T23:12:49Z","timestamp":1599433969000},"page":"361-378","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Semi-Supervised Adversarial Variational Autoencoder"],"prefix":"10.3390","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3283-9391","authenticated-orcid":false,"given":"Ryad","family":"Zemouri","sequence":"first","affiliation":[{"name":"Cedric-Lab, CNAM, HESAM Universit\u00e9, 292 rue Saint Martin, CEDEX 03, 750141 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,6]]},"reference":[{"key":"ref_1","unstructured":"Martin, G.S., Droguett, E.L., Meruane, V., and das Chagas Moura, M. (2018). Deep variational auto-encoders: A promising tool for dimensionality reduction and ball bearing elements fault diagnosis. Struct. Health Monit."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.cageo.2019.04.006","article-title":"Towards a robust parameterization for conditioning facies models using deep variational autoencoders and ensemble smoother","volume":"128","author":"Canchumuni","year":"2019","journal-title":"Comput. Geosci."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.engappai.2019.04.013","article-title":"Process monitoring using variational autoencoder for high-dimensional nonlinear processes","volume":"83","author":"Lee","year":"2019","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.jprocont.2019.01.008","article-title":"Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring","volume":"75","author":"Zhang","year":"2019","journal-title":"J. Process. Control."},{"key":"ref_5","unstructured":"Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., and Weinberger, K.Q. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems 27, Curran Associates, Inc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TCDS.2018.2883368","article-title":"Abnormal Event Detection from Videos using a Two-stream Recurrent Variational Autoencoder","volume":"12","author":"Yan","year":"2018","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1109\/TIFS.2018.2878538","article-title":"Generative Neural Networks for Anomaly Detection in Crowded Scenes","volume":"14","author":"Wang","year":"2019","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"33353","DOI":"10.1109\/ACCESS.2018.2848210","article-title":"Learning Sparse Representation With Variational Auto-Encoder for Anomaly Detection","volume":"6","author":"Sun","year":"2018","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5707","DOI":"10.1109\/ACCESS.2018.2890293","article-title":"Collaborative Additional Variational Autoencoder for Top-N Recommender Systems","volume":"7","author":"He","year":"2019","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TNNLS.2019.2900734","article-title":"Semisupervised Text Classification by Variational Autoencoder","volume":"31","author":"Xu","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"144618","DOI":"10.1109\/ACCESS.2019.2944630","article-title":"Latent Space Expanded Variational Autoencoder for Sentence Generation","volume":"7","author":"Song","year":"2019","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/TASLP.2019.2950099","article-title":"A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural F0 Model for Statistical Parametric Speech Synthesis","volume":"28","author":"Wang","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1109\/JSTSP.2019.2913965","article-title":"Modulation Filter Learning Using Deep Variational Networks for Robust Speech Recognition","volume":"13","author":"Agrawal","year":"2019","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1432","DOI":"10.1109\/TASLP.2019.2917232","article-title":"ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder","volume":"27","author":"Kameoka","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1109\/TSTE.2019.2897688","article-title":"Convolutional Graph Autoencoder: A Generative Deep Neural Network for Probabilistic Spatio-temporal Solar Irradiance Forecasting","volume":"11","author":"Khodayar","year":"2019","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"55679","DOI":"10.1109\/ACCESS.2019.2913468","article-title":"Collaborative Variational Deep Learning for Healthcare Recommendation","volume":"7","author":"Deng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.neuroimage.2019.05.039","article-title":"Variational autoencoder: An unsupervised model for encoding and decoding fMRI activity in visual cortex","volume":"198","author":"Han","year":"2019","journal-title":"NeuroImage"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1109\/TNSRE.2019.2940046","article-title":"EEG-Based Adaptive Driver-Vehicle Interface Using Variational Autoencoder and PI-TSVM","volume":"27","author":"Bi","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.gpb.2018.08.003","article-title":"VASC: Dimension Reduction and Visualization of Single-cell RNA-seq Data by Deep Variational Autoencoder","volume":"16","author":"Wang","year":"2018","journal-title":"Genom. Proteom. Bioinform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5438","DOI":"10.1109\/ACCESS.2019.2962775","article-title":"Deep Convolutional Variational Autoencoder as a 2D-Visualization Tool for Partial Discharge Source Classification in Hydrogenerators","volume":"8","author":"Zemouri","year":"2020","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.ces.2018.02.008","article-title":"Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks","volume":"181","author":"Na","year":"2018","journal-title":"Chem. Eng. Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2395","DOI":"10.1109\/LGRS.2017.2766130","article-title":"Prediction of Subsurface NMR T2 Distributions in a Shale Petroleum System Using Variational Autoencoder-Based Neural Networks","volume":"14","author":"Li","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"139086","DOI":"10.1109\/ACCESS.2019.2940769","article-title":"Motor Fault Detection and Feature Extraction Using RNN-Based Variational Autoencoder","volume":"7","author":"Huang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"22554","DOI":"10.1109\/ACCESS.2019.2894764","article-title":"Systematic Development of a New Variational Autoencoder Model Based on Uncertain Data for Monitoring Nonlinear Processes","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106515","DOI":"10.1016\/j.compchemeng.2019.106515","article-title":"A novel process monitoring approach based on variational recurrent autoencoder","volume":"129","author":"Cheng","year":"2019","journal-title":"Comput. Chem. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","article-title":"Generative Adversarial Networks: An Overview","volume":"35","author":"Creswell","year":"2018","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zemouri, R., Zerhouni, N., and Racoceanu, D. (2019). Deep Learning in the Biomedical Applications: Recent and Future Status. Appl. Sci., 9.","DOI":"10.3390\/app9081526"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/j.neucom.2018.05.024","article-title":"An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition","volume":"310","author":"Wang","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, X., Huang, H., Hu, Y., and Yang, Y. (2018, January 23\u201326). Partial Discharge Pattern Recognition with Data Augmentation based on Generative Adversarial Networks. Proceedings of the 2018 Condition Monitoring and Diagnosis (CMD), Perth, WA, Australia.","DOI":"10.1109\/CMD.2018.8535718"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1016\/j.neucom.2018.07.034","article-title":"Unsupervised fault diagnosis of rolling bearings using a deep neural network based on generative adversarial networks","volume":"315","author":"Liu","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9515","DOI":"10.1109\/ACCESS.2018.2890693","article-title":"Imbalanced Fault Diagnosis of Rolling Bearing Based on Generative Adversarial Network: A Comparative Study","volume":"7","author":"Mao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.compind.2019.01.001","article-title":"Generative adversarial networks for data augmentation in machine fault diagnosis","volume":"106","author":"Shao","year":"2019","journal-title":"Comput. Ind."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/j.knosys.2018.12.019","article-title":"A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults","volume":"165","author":"Han","year":"2019","journal-title":"Knowl. Based Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.neunet.2018.04.020","article-title":"Novel deep generative simultaneous recurrent model for efficient representation learning","volume":"107","author":"Alam","year":"2018","journal-title":"Neural Netw."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22\u201329). Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yi, Z., Zhang, H., Tan, P., and Gong, M. (2017, January 22\u201329). DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27\u201330). Context Encoders: Feature Learning by Inpainting. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref_38","unstructured":"Odena, A., Olah, C., and Shlens, J. (2016). Conditional Image Synthesis With Auxiliary Classifier GANs. arXiv."},{"key":"ref_39","unstructured":"Odena, A. (2016). Semi-Supervised Learning with Generative Adversarial Networks. arXiv."},{"key":"ref_40","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., and Smolley, S.P. (2016). Least Squares Generative Adversarial Networks. arXiv.","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref_42","unstructured":"Liu, M.Y., and Tuzel, O. (2016). Coupled Generative Adversarial Networks. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2016). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. arXiv.","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref_44","unstructured":"Kim, T., Cha, M., Kim, H., Lee, J.K., and Kim, J. (2017). Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2016). Image-to-Image Translation with Conditional Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_46","unstructured":"Hjelm, R.D., Jacob, A.P., Che, T., Trischler, A., Cho, K., and Bengio, Y. (2017). Boundary-Seeking Generative Adversarial Networks. arXiv."},{"key":"ref_47","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017). Wasserstein GAN. arXiv."},{"key":"ref_48","unstructured":"Donahue, J., Kr\u00e4henb\u00fchl, P., and Darrell, T. (2016). Adversarial Feature Learning. arXiv."},{"key":"ref_49","unstructured":"Denton, E., Gross, S., and Fergus, R. (2016). Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks. arXiv."},{"key":"ref_50","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., and Krishnan, D. (2016). Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks. arXiv.","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref_52","unstructured":"Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., Arjovsky, M., and Courville, A. (2016). Adversarially Learned Inference. arXiv."},{"key":"ref_53","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., and Frey, B. (2015). Adversarial Autoencoders. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.neucom.2019.03.013","article-title":"Improving variational autoencoder with deep feature consistent and generative adversarial training","volume":"341","author":"Hou","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"126582","DOI":"10.1109\/ACCESS.2019.2939352","article-title":"PuVAE: A Variational Autoencoder to Purify Adversarial Examples","volume":"7","author":"Hwang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., and Bethge, M. (2015). A Neural Algorithm of Artistic Style. arXiv.","DOI":"10.1167\/16.12.326"},{"key":"ref_57","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neunet.2019.05.003","article-title":"Understanding autoencoders with information theoretic concepts","volume":"117","author":"Yu","year":"2019","journal-title":"Neural Netw."},{"key":"ref_59","unstructured":"Bengio, Y. (2014). How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation. arXiv."},{"key":"ref_60","unstructured":"Im, D.J., Ahn, S., Memisevic, R., and Bengio, Y. (2015). Denoising Criterion for Variational Auto-Encoding Framework. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1016\/j.patcog.2018.12.015","article-title":"Autoencoder node saliency: Selecting relevant latent representations","volume":"88","author":"Fan","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_62","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv."},{"key":"ref_63","unstructured":"Kingma, D. (2017). Variational Inference & Deep Learning: A New Synthesis. [Ph.D. Thesis, Faculty of Science (FNWI), Informatics Institute (IVI), University of Amsterdam]."},{"key":"ref_64","unstructured":"Blei, D.M., Kucukelbir, A., and McAuliffe, J.D. (2016). Variational Inference: A Review for Statisticians. arXiv."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., and Belongie, S.J. (2016). Feature Pyramid Networks for Object Detection. arXiv.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.annpat.2019.01.004","article-title":"Intelligence artificielle: Quel avenir en anatomie pathologique?","volume":"39","author":"Zemouri","year":"2019","journal-title":"Ann. Pathol."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_68","unstructured":"Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., and Weinberger, K.Q. (2013). One-shot learning by inverting a compositional causal process. Advances in Neural Information Processing Systems 26, Curran Associates, Inc."},{"key":"ref_69","first-page":"509","article-title":"Inductive Principles for Restricted Boltzmann Machine Learning","volume":"Volume 9","author":"Teh","year":"2010","journal-title":"Machine Learning Research, Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13\u201315 May 2010"},{"key":"ref_70","unstructured":"Xiao, H., Rasul, K., and Vollgraf, R. (2017). Fashion-MNIST: A Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv."},{"key":"ref_71","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images. [Master\u2019s Thesis, Department of Computer Science, University of Toronto]."}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/20\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:07:20Z","timestamp":1760177240000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/2\/3\/20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,6]]},"references-count":71,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["make2030020"],"URL":"https:\/\/doi.org\/10.3390\/make2030020","relation":{"has-preprint":[{"id-type":"doi","id":"10.20944\/preprints202008.0051.v1","asserted-by":"object"}]},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,6]]}}}