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
来源
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2021年
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
  • [41] STATISTICAL COMPRESSIVE SENSING OF GAUSSIAN MIXTURE MODELS
    Yu, Guoshen
    Sapiro, Guillermo
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 3728 - 3731
  • [42] Reduction of Gaussian mixture models by maximum similarity
    Harmse, Jorgen E.
    JOURNAL OF NONPARAMETRIC STATISTICS, 2010, 22 (06) : 703 - 709
  • [43] Skew Gaussian mixture models for speaker recognition
    Matza, Avi
    Bistritz, Yuval
    12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 12 - 15
  • [44] Deep convolutional features for image retrieval
    Gkelios, Socratis
    Sophokleous, Aphrodite
    Plakias, Spiros
    Boutalis, Yiannis
    Chatzichristofis, Savvas A.
    EXPERT SYSTEMS WITH APPLICATIONS, 2021, 177
  • [45] Ice-Core Micro-CT Image Segmentation With Deep Learning and Gaussian Mixture Model
    Bagherzadeh, Faramarz
    Freitag, Johannes
    Frese, Udo
    Wilhelms, Frank
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 : 1 - 11
  • [46] Particle Swarm Optimization Algorithm based Gaussian Mixture Models for Remote-Sensing Image Recognition
    Zhang Jianhua
    Zhou Hong
    2014 33RD CHINESE CONTROL CONFERENCE (CCC), 2014, : 4658 - 4663
  • [47] Statistical convergence of the EM algorithm on Gaussian mixture models
    Zhao, Ruofei
    Li, Yuanzhi
    Sun, Yuekai
    ELECTRONIC JOURNAL OF STATISTICS, 2020, 14 (01): : 632 - 660
  • [48] Fast Reinforcement Learning with Incremental Gaussian Mixture Models
    Pinto, Rafael
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [49] On the characterization of flowering curves using Gaussian mixture models
    Proia, Frederic
    Pernet, Alix
    Thouroude, Tatiana
    Michel, Gilles
    Clotault, Jeremy
    JOURNAL OF THEORETICAL BIOLOGY, 2016, 402 : 75 - 88
  • [50] Full Covariance Gaussian Mixture Models Evaluation on GPU
    Vanek, Jan
    Trmal, Jan
    Psutka, Josef V.
    Psutka, Josef
    2012 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT), 2012, : 203 - 207