Výsledky vyhledávání - semi-supervised conventional variational autoencoder

  1. 1

    SS-VPE: Semi-Supervised Variational Prototyping Encoder with Student's-t Mixture Model Autor Liu, Yukun, Shi, Daming

    ISSN: 0018-9456, 1557-9662
    Vydáno: New York IEEE 01.01.2023
    “… However, a latent prototype is mostly sensitive to outliers; therefore, a general method using a semi-supervised variational prototyping encoder (SS-VPE) is proposed…”
    Získat plný text
    Journal Article
  2. 2

    Developing semi-supervised variational autoencoder-generative adversarial network models to enhance quality prediction performance Autor Ooi, Sai Kit, Tanny, Dave, Chen, Junghui, Wang, Kai

    ISSN: 0169-7439, 1873-3239
    Vydáno: Elsevier B.V 15.10.2021
    “… Such discrepancy exists because of the time lag for obtaining quality data. This paper proposes semi-supervised variational autoencoder-generative adversarial network (S2-VAE/GAN…”
    Získat plný text
    Journal Article
  3. 3

    A Semi-supervised Gaussian Mixture Variational Autoencoder method for few-shot fine-grained fault diagnosis Autor Zhao, Zhiqian, Xu, Yeyin, Zhang, Jiabin, Zhao, Runchao, Chen, Zhaobo, Jiao, Yinghou

    ISSN: 0893-6080, 1879-2782, 1879-2782
    Vydáno: United States Elsevier Ltd 01.10.2024
    Vydáno v Neural networks (01.10.2024)
    “… To tackle those issue, we propose a novel semi-supervised Gaussian Mixed Variational Autoencoder method, SeGMVAE, aimed at acquiring unsupervised representations that can be transferred across fine…”
    Získat plný text
    Journal Article
  4. 4

    Semi-Supervised Adversarial Variational Autoencoder Autor Zemouri, Ryad

    ISSN: 2504-4990, 2504-4990
    Vydáno: MDPI 01.09.2020
    “…We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE…”
    Získat plný text
    Journal Article
  5. 5

    Developing semi-supervised latent dynamic variational autoencoders to enhance prediction performance of product quality Autor Lee, Yi Shan, Chen, Junghui

    ISSN: 0009-2509, 1873-4405
    Vydáno: Elsevier Ltd 16.01.2023
    Vydáno v Chemical engineering science (16.01.2023)
    “…•Dynamic features of process and quality data are learned for quality prediction.•Bi-directional RNN is trained by past and future data to prevent…”
    Získat plný text
    Journal Article
  6. 6

    S2VQ-VAE: Semi-Supervised Vector Quantised-Variational AutoEncoder for Automatic Evaluation of Trail Making Test Autor Tang, Zeshen, Tang, Shiyu, Wang, Haoran, Li, Renren, Zhang, Xiaochen, Zhang, Wei, Yuan, Xiao, Zang, Yaning, Li, Yanping, Zhou, Tian, Li, Yunxia

    ISSN: 2168-2194, 2168-2208, 2168-2208
    Vydáno: United States IEEE 01.08.2024
    “… We proposed a novel deep representation learning approach named Semi-Supervised Vector Quantised-Variational AutoEncoder (S2VQ-VAE…”
    Získat plný text
    Journal Article
  7. 7

    Physics-informed variational autoencoders for improved robustness to environmental factors of variation Autor Thoreau, Romain, Risser, Laurent, Achard, Véronique, Berthelot, Béatrice, Briottet, Xavier

    ISSN: 0885-6125, 1573-0565
    Vydáno: New York Springer US 01.09.2025
    Vydáno v Machine learning (01.09.2025)
    “… In this paper, we introduce p 3 VAE, a variational autoencoder that integrates prior physical knowledge modeling the generative latent factors of variation that are related to the data acquisition conditions…”
    Získat plný text
    Journal Article
  8. 8

    Guided Variational Autoencoder for Speech Enhancement with a Supervised Classifier Autor Carbajal, Guillaume, Richter, Julius, Gerkmann, Timo

    ISSN: 2379-190X
    Vydáno: IEEE 06.06.2021
    “…Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement…”
    Získat plný text
    Konferenční příspěvek
  9. 9

    Anomaly Detection Based on Graph Convolutional Network–Variational Autoencoder Model Using Time-Series Vibration and Current Data Autor Choi, Seung-Hwan, An, Dawn, Lee, Inho, Lee, Suwoong

    ISSN: 2227-7390, 2227-7390
    Vydáno: Basel MDPI AG 01.12.2024
    Vydáno v Mathematics (Basel) (01.12.2024)
    “… To address this issue, we employ a semi-supervised learning approach that relies solely on normal data to effectively detect abnormal patterns, overcoming the limitations of conventional methods…”
    Získat plný text
    Journal Article
  10. 10

    Novel Semi-Supervised Seasonal-Trend VTN for Multimode Process IoT Soft Sensing Autor He, Yan-Lin, Zhou, Yang-Xiao-Yu, Xu, Yuan, Zhu, Qun-Xiong, Li, Xingyuan

    ISSN: 2327-4662, 2327-4662
    Vydáno: Piscataway IEEE 15.11.2025
    Vydáno v IEEE internet of things journal (15.11.2025)
    “… However, modern process industries involve highly dynamic systems with multimode and nonlinear data, posing challenges for conventional soft sensor models that assume uniform data distributions…”
    Získat plný text
    Journal Article
  11. 11

    Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization Autor Bando, Yoshiaki, Mimura, Masato, Itoyama, Katsutoshi, Yoshii, Kazuyoshi, Kawahara, Tatsuya

    ISSN: 2379-190X
    Vydáno: IEEE 01.04.2018
    “…This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE…”
    Získat plný text
    Konferenční příspěvek
  12. 12

    Semi-Supervised Source Localization With Residual Physical Learning Autor Bianco, Michael J., Gerstoft, Peter

    ISSN: 2379-190X
    Vydáno: IEEE 23.05.2022
    “… This challenge has recently been addressed using semi-supervised learning (SSL) based on deep generative modeling with variational autoencoders…”
    Získat plný text
    Konferenční příspěvek
  13. 13

    Speech Enhancement with Variational Autoencoders and Alpha-stable Distributions Autor Leglaive, Simon, Simsekli, Umut, Liutkus, Antoine, Girin, Laurent, Horaud, Radu

    ISSN: 2379-190X
    Vydáno: IEEE 01.05.2019
    “…This paper focuses on single-channel semi-supervised speech enhancement. We learn a speaker-independent deep generative speech model using the framework of variational autoencoders…”
    Získat plný text
    Konferenční příspěvek
  14. 14

    Gated Mixture Variational Autoencoders for Value Added Tax audit case selection Autor Kleanthous, Christos, Chatzis, Sotirios

    ISSN: 0950-7051, 1872-7409
    Vydáno: Amsterdam Elsevier B.V 05.01.2020
    Vydáno v Knowledge-based systems (05.01.2020)
    “… This gives rise to a semi-supervised learning framework that leverages the latest advances in deep learning and robust regularization using variational inference…”
    Získat plný text
    Journal Article
  15. 15

    Entropy optimized semi-supervised decomposed vector-quantized variational autoencoder model based on transfer learning for multiclass text classification and generation Autor Malhotra, Shivani, Kumar, Vinay, Agarwal, Alpana

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 10.11.2021
    Vydáno v arXiv.org (10.11.2021)
    “…Semisupervised text classification has become a major focus of research over the past few years. Hitherto, most of the research has been based on supervised…”
    Získat plný text
    Paper
  16. 16

    Vehicular Trajectory Classification and Traffic Anomaly Detection in Videos Using a Hybrid CNN-VAE Architecture Autor Kumaran Santhosh, Kelathodi, Dogra, Debi Prosad, Roy, Partha Pratim, Mitra, Adway

    ISSN: 1524-9050, 1558-0016
    Vydáno: New York IEEE 01.08.2022
    “…) and Variational Autoencoder (VAE) architecture. First, we introduce a high level features for varying length object trajectories using color gradient representation…”
    Získat plný text
    Journal Article
  17. 17

    A Transformer–VAE Approach for Detecting Ship Trajectory Anomalies in Cross-Sea Bridge Areas Autor Hou, Jiawei, Zhou, Hongzhu, Grifoll, Manel, Zhou, Yusheng, Liu, Jiao, Ye, Yun, Zheng, Pengjun

    ISSN: 2077-1312, 2077-1312
    Vydáno: Basel MDPI AG 01.05.2025
    “… Most existing anomaly detection methods heavily rely on labeled or semi-supervised data, thus limiting their applicability in scenarios involving completely unlabeled ship trajectory data…”
    Získat plný text
    Journal Article
  18. 18

    Semi-Supervised Source Localization in Reverberant Environments With Deep Generative Modeling Autor Bianco, Michael J., Gannot, Sharon, Fernandez-Grande, Efren, Gerstoft, Peter

    ISSN: 2169-3536, 2169-3536
    Vydáno: Piscataway IEEE 2021
    Vydáno v IEEE access (2021)
    “… We propose to address this issue with a semi-supervised learning (SSL) approach, based on deep generative modeling…”
    Získat plný text
    Journal Article
  19. 19

    Anomaly based Resilient Network Intrusion Detection using Inferential Autoencoders Autor Hannan, Abdul, Gruhl, Christian, Sick, Bernhard

    Vydáno: IEEE 26.07.2021
    “…This article focuses on the application of conditional variational autoencoders as anomaly detectors to identify emerging threats in computer networks…”
    Získat plný text
    Konferenční příspěvek
  20. 20

    Multi-Modal Sentiment Classification With Independent and Interactive Knowledge via Semi-Supervised Learning Autor Zhang, Dong, Li, Shoushan, Zhu, Qiaoming, Zhou, Guodong

    ISSN: 2169-3536, 2169-3536
    Vydáno: Piscataway IEEE 2020
    Vydáno v IEEE access (2020)
    “… The key idea is to leverage the semi-supervised variational autoencoders to mine more information from unlabeled data for multi-modal sentiment analysis…”
    Získat plný text
    Journal Article