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
  • [21] Image data source selection using Gaussian mixture models
    El Allah, Soufyane
    Blank, Daniel
    Mueller, Wolfgang
    Henrich, Andreas
    ADAPTIVE MULTIMEDIAL RETRIEVAL: RETRIEVAL, USER, AND SEMANTICS, 2008, 4918 : 170 - 181
  • [22] Image segmentation using spectral clustering of Gaussian mixture models
    Zeng, Shan
    Huang, Rui
    Kang, Zhen
    Sang, Nong
    NEUROCOMPUTING, 2014, 144 : 346 - 356
  • [23] Image Segmentation by Gaussian Mixture Models and Modified FCM Algorithm
    Kalti, Karim
    Mahjoub, Mohamed
    INTERNATIONAL ARAB JOURNAL OF INFORMATION TECHNOLOGY, 2014, 11 (01) : 11 - 18
  • [24] Gaussian mixture models of texture and colour for image database retrieval
    Permuter, H
    Francos, J
    Jermyn, IH
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL III, PROCEEDINGS: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING SIGNAL, PROCESSING EDUCATION, 2003, : 569 - 572
  • [25] Color image segmentation through unsupervised Gaussian mixture models
    Penalver, Antonio
    Escolano, Francisco
    Saez, Juan M.
    ADVANCES IN ARTIFICIAL INTELLIGENCE - IBERAMIA-SBIA 2006, PROCEEDINGS, 2006, 4140 : 149 - 158
  • [26] Image Classification Based On Deep Convolutional Network And Gaussian Aggregate Encoding
    Wang, Fengge
    Tian, Xiaolin
    Zhang, Yang
    Jia, Nan
    Lu, Tiantian
    2020 IEEE 32ND INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI), 2020, : 540 - 544
  • [27] Deep Convolutional Gaussian Processes
    Blomqvist, Kenneth
    Kaski, Samuel
    Heinonen, Markus
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2019, PT II, 2020, 11907 : 582 - 597
  • [28] Deep Convolutional Gaussian Mixture Model for Stain-Color Normalization of Histopathological Images
    Zanjani, Farhad Ghazvinian
    Zinger, Svitlana
    de With, Peter H. N.
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2018, PT II, 2018, 11071 : 274 - 282
  • [29] Sparse representation optimization of image Gaussian mixture features based on a convolutional neural network
    Ye, Fangfang
    Ren, Tiaojuan
    Wang, Zhangquan
    Wang, Ting
    NEURAL COMPUTING & APPLICATIONS, 2022, 34 (15): : 12427 - 12437
  • [30] Sparse representation optimization of image Gaussian mixture features based on a convolutional neural network
    Fangfang Ye
    Tiaojuan Ren
    Zhangquan Wang
    Ting Wang
    Neural Computing and Applications, 2022, 34 : 12427 - 12437