MisConv: Convolutional Neural Networks for Missing Data

被引:4
|
作者
Likowski, Marcin Przewiez [1 ]
Smieja, Marek [1 ]
Struski, Lukasz [1 ]
Tabor, Jacek [1 ]
机构
[1] Jagiellonian Univ, Fac Math & Comp Sci, 6 Lojasiewicza St, PL-30348 Krakow, Poland
关键词
CHAINED EQUATIONS; IMPUTATION; MACHINE; VALUES;
D O I
10.1109/WACV51458.2022.00297
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image inpainting or autonomous vehicles and robots. While imputation-based techniques are still one of the most popular solutions, they frequently introduce unreliable information to the data and do not take into account the uncertainty of estimation, which may be destructive for a machine learning model. In this paper, we present MisConv, a general mechanism, for adapting various CNN architectures to process incomplete images. By modeling the distribution of missing values by the Mixture of Factor Analyzers, we cover the spectrum of possible replacements and find an analytical formula for the expected value of convolution operator applied to the incomplete image. The whole framework is realized by matrix operations, which makes MisConv extremely efficient in practice. Experiments performed on various image processing tasks demonstrate that MisConv achieves superior or comparable performance to the state-of-the-art methods.
引用
收藏
页码:2917 / 2926
页数:10
相关论文
共 50 条
  • [21] Tailoring convolutional neural networks for custom botanical data
    Sykes, Jamie R.
    Denby, Katherine J.
    Franks, Daniel W.
    APPLICATIONS IN PLANT SCIENCES, 2025, 13 (01):
  • [22] A Robotized Data Collection Approach for Convolutional Neural Networks
    Liu, Yiming
    Zhang, Shaohua
    Xiao, Xiaohui
    Li, Miao
    INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2017, PT III, 2017, 10464 : 472 - 483
  • [23] GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR HYPERSPECTRAL DATA CLASSIFICATION
    Shahraki, Farideh Foroozandeh
    Prasad, Saurabh
    2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2018), 2018, : 968 - 972
  • [24] Further Advantages of Data Augmentation on Convolutional Neural Networks
    Hernandez-Garcia, Alex
    Koenig, Peter
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT I, 2018, 11139 : 95 - 103
  • [25] The Use of Convolutional Neural Networks in Biomedical Data Processing
    Bursa, Miroslav
    Lhotska, Lenka
    INFORMATION TECHNOLOGY IN BIO- AND MEDICAL INFORMATICS, ITBAM 2017, 2017, 10443 : 100 - 119
  • [26] Photoacoustic microscopy with sparse data by convolutional neural networks
    Zhou, Jiasheng
    He, Da
    Shang, Xiaoyu
    Guo, Zhendong
    Chen, Sung-Liang
    Luo, Jiajia
    PHOTOACOUSTICS, 2021, 22
  • [27] Generalized Convolutional Neural Networks for Point Cloud Data
    Savchenkov, Aleksandr
    Davis, Andrew
    Zhao, Xuan
    2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2017, : 930 - 935
  • [28] Convolutional Neural Networks at the Interface of Physical and Digital Data
    Ushizima, Daniela
    Yang, Chao
    Venkatakrishnan, Singanallur
    Araujo, Flavio
    Silva, Romuere
    Tang, Haoran
    Mascarenhas, Joao Vitor
    Hexemer, Alex
    Parkinson, Dilworth
    Sethian, James
    2016 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2016,
  • [29] Data Augmentation for Drum Transcription with Convolutional Neural Networks
    Jacques, Celine
    Roebel, Axel
    2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
  • [30] Towards Near Data Processing of Convolutional Neural Networks
    Das, Palash
    Lakhotia, Shivam
    Shetty, Prabodh
    Kapoor, Hemangee K.
    2018 31ST INTERNATIONAL CONFERENCE ON VLSI DESIGN AND 2018 17TH INTERNATIONAL CONFERENCE ON EMBEDDED SYSTEMS (VLSID & ES), 2018, : 380 - 385