Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (19): 139-145.DOI: 10.3778/j.issn.1002-8331.1907-0284

Previous Articles     Next Articles

Visual Analysis of Deep Convolutional Neural Networks in Parallel Vision Framework

ZHAI Yongjie, YANG Xu, WANG Jinna, WANG Kunfeng, ZHAO Zhenbing   

  1. 1.Department of Automation, North China Electric Power University, Baoding, Hebei 071003, China
    2.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
    3.Department of Electronic and Communications Engineering, North China Electric Power University, Baoding, Hebei 071003, China
  • Online:2020-10-01 Published:2020-09-29



  1. 1.华北电力大学 自动化系,河北 保定 071003
    2.中国科学院 自动化研究所 复杂系统管理与控制国家重点实验室,北京 100190
    3.华北电力大学 电子与通讯工程系,河北 保定 071003


Deep learning methods have made great progress in the field of computer vision, various deep convolutional neural networks have achieved good application effects in actual target detection, but the interpretability of the network is poor. The feature map is reversely mapped to the pixel space of the input image and the feature map of the network is visualized for analysis; under the framework of parallel vision research, the feature response of the network is analyzed with real and artificial insulator image samples, the network parameters are adjusted according to the visualization results. The results show that the artificial samples with different proportions, angles and positions have different effects on the accuracy of the network, the characteristic response of the network is also different. The structure and parameters of the network are adjusted according to the visualization results of the feature graph, which improves the performance of the network.

Key words: parallel vision, convolutional neural network, visualization, characteristic response



关键词: 平行视觉, 卷积神经网络, 可视化, 特征响应