A Deep Convolutional Generative Adversarial Networks (DCGANs)-Based Semi-Supervised Method for Object Recognition in Synthetic Aperture Radar (SAR) Images

被引:110
|
作者
Gao, Fei [1 ]
Yang, Yue [1 ]
Wang, Jun [1 ]
Sun, Jinping [1 ]
Yang, Erfu [2 ]
Zhou, Huiyu [3 ]
机构
[1] Beihang Univ, Elect Informat Engn, Beijing 100191, Peoples R China
[2] Univ Strathclyde, Dept Design Mfg & Engn, Space Mechatron Syst Technol Lab, Management, Glasgow G11XJ, Lanark, Scotland
[3] Univ Leicester, Dept Informat, Leicester LE1 7RH, Leics, England
基金
英国工程与自然科学研究理事会; 中国国家自然科学基金;
关键词
SAR target recognition; semi-supervised; DCGANs; joint training; TARGET RECOGNITION; SCENE CLASSIFICATION; EXTRACTION; MODEL;
D O I
10.3390/rs10060846
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Synthetic aperture radar automatic target recognition (SAR-ATR) has made great progress in recent years. Most of the established recognition methods are supervised, which have strong dependence on image labels. However, obtaining the labels of radar images is expensive and time-consuming. In this paper, we present a semi-supervised learning method that is based on the standard deep convolutional generative adversarial networks (DCGANs). We double the discriminator that is used in DCGANs and utilize the two discriminators for joint training. In this process, we introduce a noisy data learning theory to reduce the negative impact of the incorrectly labeled samples on the performance of the networks. We replace the last layer of the classic discriminators with the standard softmax function to output a vector of class probabilities so that we can recognize multiple objects. We subsequently modify the loss function in order to adapt to the revised network structure. In our model, the two discriminators share the same generator, and we take the average value of them when computing the loss function of the generator, which can improve the training stability of DCGANs to some extent. We also utilize images of higher quality from the generated images for training in order to improve the performance of the networks. Our method has achieved state-of-the-art results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset, and we have proved that using the generated images to train the networks can improve the recognition accuracy with a small number of labeled samples.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition
    Zhenyu Yue
    Fei Gao
    Qingxu Xiong
    Jun Wang
    Teng Huang
    Erfu Yang
    Huiyu Zhou
    [J]. Cognitive Computation, 2021, 13 : 795 - 806
  • [2] A Novel Semi-Supervised Convolutional Neural Network Method for Synthetic Aperture Radar Image Recognition
    Yue, Zhenyu
    Gao, Fei
    Xiong, Qingxu
    Wang, Jun
    Huang, Teng
    Yang, Erfu
    Zhou, Huiyu
    [J]. COGNITIVE COMPUTATION, 2021, 13 (04) : 795 - 806
  • [3] Semi-Supervised Encrypted Traffic Classification With Deep Convolutional Generative Adversarial Networks
    Iliyasu, Auwal Sani
    Deng, Huifang
    [J]. IEEE ACCESS, 2020, 8 : 118 - 126
  • [4] SEMI-SUPERVISED OBJECT DETECTION IN REMOTE SENSING IMAGES USING GENERATIVE ADVERSARIAL NETWORKS
    Chen, Guowei
    Liu, Lei
    Hu, Wenlong
    Pan, Zongxu
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 2503 - 2506
  • [5] Radio Classify Generative Adversarial Networks: A Semi-supervised Method for Modulation Recognition
    Li, Mingxuan
    Liu, Guangyi
    Li, Shuntao
    Wu, Yifan
    [J]. 2018 IEEE 18TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY (ICCT), 2018, : 669 - 672
  • [6] Semi-supervised community detection method based on generative adversarial networks
    Liu, Xiaoyang
    Zhang, Mengyao
    Liu, Yanfei
    Liu, Chao
    Li, Chaorong
    Wang, Wei
    Zhang, Xiaoqin
    Bouyer, Asgarali
    [J]. JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2024, 36 (03)
  • [7] Hardness Recognition of Robotic Forearm Based on Semi-supervised Generative Adversarial Networks
    Qian, Xiaoliang
    Li, Erkai
    Zhang, Jianwei
    Zhao, Su-Na
    Wu, Qing-E
    Zhang, Huanlong
    Wang, Wei
    Wu, Yuanyuan
    [J]. FRONTIERS IN NEUROROBOTICS, 2019, 13
  • [8] Semi-Supervised Generative Adversarial Nets with Multiple Generators for SAR Image Recognition
    Gao, Fei
    Ma, Fei
    Wang, Jun
    Sun, Jinping
    Yang, Erfu
    Zhou, Huiyu
    [J]. SENSORS, 2018, 18 (08)
  • [9] General image classification method based on semi-supervised generative adversarial networks
    苏磊
    Xu Xiangyi
    Lu Qiyu
    Zhang Wancai
    [J]. High Technology Letters, 2019, 25 (01) : 35 - 41
  • [10] Automatic Target Recognition for Synthetic Aperture Radar Images Based on Super-Resolution Generative Adversarial Network and Deep Convolutional Neural Network
    Shi, Xiaoran
    Zhou, Feng
    Yang, Shuang
    Zhang, Zijing
    Su, Tao
    [J]. REMOTE SENSING, 2019, 11 (02)