Image Modeling with Deep Convolutional Gaussian Mixture Models

被引:0
|
作者
Gepperth, Alexander [1 ]
Pfuelb, Benedikt [1 ]
机构
[1] Fulda Univ Appl Sci, Fulda, Germany
关键词
Deep Learning; Gaussian Mixture Models; Deep Convolutional Gaussian Mixture Models; Stochastic Gradient Descent;
D O I
10.1109/IJCNN52387.2021.9533745
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this conceptual work, we present Deep Convolutional Gaussian Mixture Models (DCGMMs): a new formulation of deep hierarchical Gaussian Mixture Models (GMMs) that is particularly suitable for describing and generating images. Vanilla (i.e., flat) GMMs require a very large number of components to describe images well, leading to long training times and memory issues. DCGMMs avoid this by a stacked architecture of multiple GMM layers, linked by convolution and pooling operations. This allows to exploit the compositionality of images in a similar way as deep CNNs do. DCGMMs can be trained end-to-end by Stochastic Gradient Descent. This sets them apart from vanilla GMMs which are trained by Expectation-Maximization, requiring a prior k-means initialization which is infeasible in a layered structure. For generating sharp images with DCGMMs, we introduce a new gradient-based technique for sampling through non-invertible operations like convolution and pooling. Based on the MNIST and FashionMNIST datasets, we validate the DCGMMs model by demonstrating its superiority over flat GMMs for clustering, sampling and outlier detection.
引用
收藏
页数:9
相关论文
共 50 条
  • [31] Deep LSTM Enhancement for RUL Prediction Using Gaussian Mixture Models
    Sayah, M.
    Guebli, D.
    Noureddine, Z.
    Al Masry, Z.
    AUTOMATIC CONTROL AND COMPUTER SCIENCES, 2021, 55 (01) : 15 - 25
  • [32] Document image binarization using local features and Gaussian mixture modeling
    Mitianoudis, Nikolaos
    Papamarkos, Nikolaos
    IMAGE AND VISION COMPUTING, 2015, 38 : 33 - 51
  • [33] Graph representation learning based on deep generative gaussian mixture models
    Niknam, Ghazaleh
    Molaei, Soheila
    Zare, Hadi
    Clifton, David
    Pan, Shirui
    NEUROCOMPUTING, 2023, 523 : 157 - 169
  • [34] Self-Growing Regularized Gaussian Mixture Models for Image Segmentation
    Guan, Tao
    Wang, Hongxia
    Wang, Yan
    PROCEEDINGS OF THE 2012 INTERNATIONAL CONFERENCE ON COMMUNICATION, ELECTRONICS AND AUTOMATION ENGINEERING, 2013, 181 : 577 - 582
  • [35] Image retrieval using spatiograms of colors quantized by Gaussian Mixture Models
    Zeng, Shan
    Huang, Rui
    Wang, Haibing
    Kang, Zhen
    NEUROCOMPUTING, 2016, 171 : 673 - 684
  • [36] Deep LSTM Enhancement for RUL Prediction Using Gaussian Mixture Models
    M. Sayah
    D. Guebli
    Z. Noureddine
    Z. Al Masry
    Automatic Control and Computer Sciences, 2021, 55 : 15 - 25
  • [37] Image Restoration Based on Improved Patch Clustering in Gaussian Mixture Models
    Qiu, Guoqing
    Wei, Yating
    Yang, Haijing
    Wang, Yantao
    Luo, Pan
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 4502 - 4505
  • [38] A robust aerial image registration method using Gaussian mixture models
    Wu, Chuan
    Wang, Yuanyuan
    Karimi, Hamid Reza
    NEUROCOMPUTING, 2014, 144 : 546 - 552
  • [40] Automatic Image Equalization and Contrast Enhancement Using Gaussian Mixture Modeling
    Celik, Turgay
    Tjahjadi, Tardi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2012, 21 (01) : 145 - 156