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
  • [41] Medical Image Segmentation using Characteristic Function of Gaussian Mixture Models
    Song, Yuqing
    Xie, Conghua
    Chen, Jianmei
    2010 3RD INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND INFORMATICS (BMEI 2010), VOLS 1-7, 2010, : 375 - 379
  • [42] Interactive image segmentation based on Gaussian Mixture Models with spatial prior
    Yan, Mo
    Shui, Peng-Lang
    International Journal of Multimedia and Ubiquitous Engineering, 2015, 10 (07): : 105 - 114
  • [43] q-Gaussian mixture models for image and video semantic indexing
    Inoue, Nakamasa
    Shinoda, Koichi
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2013, 24 (08) : 1450 - 1457
  • [44] An analytic distance metric for Gaussian mixture models with application in image retrieval
    Sfikas, G
    Constantinopoulos, C
    Likas, A
    Galatsanos, NP
    ARTIFICIAL NEURAL NETWORKS: FORMAL MODELS AND THEIR APPLICATIONS - ICANN 2005, PT 2, PROCEEDINGS, 2005, 3697 : 835 - 840
  • [45] Estimating the number of components in Gaussian mixture models adaptively for medical image
    Xie, Cong-Hua
    Chang, Jin-Yi
    Liu, Yong-Jun
    OPTIK, 2013, 124 (23): : 6216 - 6221
  • [46] Gaussian Mixture Models Improve fMRI-based Image Reconstruction
    Schoenmakers, Sanne
    van Gerven, Marcel
    Heskes, Tom
    2014 INTERNATIONAL WORKSHOP ON PATTERN RECOGNITION IN NEUROIMAGING, 2014,
  • [47] NGMMs: Neutrosophic Gaussian Mixture Models for Breast Ultrasound Image Classification
    Huang, Kuan
    Xu, Meng
    Qi, Xiaojun
    2021 43RD ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY (EMBC), 2021, : 3943 - 3947
  • [48] Novel Image Registration Method Using Multiple Gaussian Mixture Models
    Ye, Peng
    Liu, Fang
    PROCEEDINGS OF 2012 2ND INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2012), 2012, : 2117 - 2120
  • [49] Deep Gaussian Mixture Ensembles
    El-Laham, Yousef
    Dalmasso, Niccolo
    Fons, Elizabeth
    Vyetrenko, Svitlana
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2023, 216 : 549 - 559
  • [50] Roller Bearing Failure Analysis using Gaussian Mixture Models and Convolutional Neural Networks
    Rathore, Maan Singh
    Harsha, S. P.
    JOURNAL OF FAILURE ANALYSIS AND PREVENTION, 2022, 22 (05) : 1853 - 1871