ROBUSTNESS OF DEEP CONVOLUTIONAL NEURAL NETWORKS FOR IMAGE DEGRADATIONS

被引：0
|
作者：
Ghosh, Sanjukta [1 ,2 ]
Shet, Rohan [1 ,2 ]
Amon, Peter [2 ]
Hutter, Andreas [2 ]
Kaup, Andre [1 ]
机构：
[1] Friedrich Alexander Univ Erlangen Nurnberg FAU, Multimedia Commun & Signal Proc, Erlangen, Germany
[2] Siemens Corp Technol, Sensing & Ind Imaging, Munich, Germany
来源：
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年
关键词：
Deep convolutional neural networks; robustness; image compression; noise; blur;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Deep convolutional neural networks (CNNs) have achieved tremendous success in image recognition tasks. However, the performance of CNNs degrade in situations where the input image is degraded by compression artifacts, blur or noise. In this paper, we analyze some of the common CNNs for degradations in images caused by Gaussian noise, blur as well as compression using JPEG and JPEG 2000 for the full range of quality factors. Moreover, we propose a method to improve the performance of CNNs for image classification in the presence of input images with degradations based on a master-slave architecture. Our method was found to perform well for individual and combined degradations.
引用
收藏
页码：2916 / 2920
页数：5
相关论文
共 50 条
  • [1] Robustness of Deep Convolutional Neural Networks for Image Recognition
    Ulicny, Matej
    Lundstrom, Jens
    Byttner, Stefan
    [J]. INTELLIGENT COMPUTING SYSTEMS, 2016, 597 : 16 - 30
  • [2] Intelligent Localization of Transformer Internal Degradations Combining Deep Convolutional Neural Networks and Image Segmentation
    Duan, Jiajun
    He, Yigang
    Du, Bolun
    Ghandour, Ruaa M. Rashad
    Wu, Wenjie
    Zhang, Hui
    [J]. IEEE ACCESS, 2019, 7 : 62705 - 62720
  • [3] Dealing with Robustness of Convolutional Neural Networks for Image Classification
    Arcaini, Paolo
    Bombarda, Andrea
    Bonfanti, Silvia
    Gargantini, Angelo
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE TESTING (AITEST), 2020, : 7 - 14
  • [4] DEEP CONVOLUTIONAL NEURAL NETWORKS FEATURES FOR IMAGE RETRIEVAL
    Kanaparthi, Suresh kumar
    Raju, U. S. N.
    [J]. ADVANCES AND APPLICATIONS IN MATHEMATICAL SCIENCES, 2021, 20 (11): : 2613 - 2626
  • [5] Histopathological Image Classification with Deep Convolutional Neural Networks
    Alom, Md Zahangir
    Aspiras, Theus
    Taha, Tarek M.
    Asari, Vijayan K.
    [J]. APPLICATIONS OF MACHINE LEARNING, 2019, 11139
  • [6] Evolving Deep Convolutional Neural Networks for Image Classification
    Sun, Yanan
    Xue, Bing
    Zhang, Mengjie
    Yen, Gary G.
    [J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2020, 24 (02) : 394 - 407
  • [7] Deep Convolutional Neural Networks for Hyperspectral Image Classification
    Hu, Wei
    Huang, Yangyu
    Wei, Li
    Zhang, Fan
    Li, Hengchao
    [J]. JOURNAL OF SENSORS, 2015, 2015
  • [8] Quantifying Degradations of Convolutional Neural Networks in Space Environments
    Altland, Emily
    Castellanos, Jonathan
    Detwiler, Joshua
    Fermin, Paolo
    Ferra, Raquel
    Kelly, Conor
    Latoski, Casey
    Ma, Tiffany
    Maher, Thomas
    Kuzin, Julia Mahon
    Mohammadian, Ali
    Abdalla, Abdelrahman Said
    Headley, William C.
    Michaels, Alan J.
    [J]. 2019 IEEE COGNITIVE COMMUNICATIONS FOR AEROSPACE APPLICATIONS WORKSHOP (CCAAW), 2019,
  • [9] Deep OCT image compression with convolutional neural networks
    Guo, Pengfei
    Li, Dawei
    Li, Xingde
    [J]. BIOMEDICAL OPTICS EXPRESS, 2020, 11 (07): : 3543 - 3554
  • [10] Improving Robustness of Medical Image Diagnosis with Denoising Convolutional Neural Networks
    Xue, Fei-Fei
    Peng, Jin
    Wang, Ruixuan
    Zhang, Qiong
    Zheng, Wei-Shi
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT VI, 2019, 11769 : 846 - 854
12345