联合生成对抗网络和检测网络的SAR图像目标检测

针对合成孔径雷达图像目标检测中存在的样本获取困难且数量有限问题,提出了联合生成对抗网络和检测网络的学习模型。利用原始训练集对特别设计的超快区域卷积神经网络进行预训练；再通过基于注意力机制的深度学习生成对抗网络生成高质量合成样本,并输入检测网络进行预测；依据预测信息和概率等价类属标签分配策略为新生样本提供注释信息,并以一定占比对原始训练集进行扩充；利用扩充数据集对检测网络进行再训练。多组仿真实验证明,所提框架能够有效提升网络检测效率和性能。

Target detection in SAR images based on joint generative adversarial network and detection network

Aiming at the problem of difficult and limited sample acquisition in SAR image target detection, a learning model of joint GAN (generative adversarial network) and detection network was proposed. The original training set is used to pre train the specially designed faster regional convolutional neural network. The deep convolutional GAN based on attention mechanism was employed to generate extensive synthetic samples, which were input into the trained specially designed faster region-based convolutional neural network for prediction. The corresponding annotation information of the new samples was determined by the prediction information and probability equivalent class label allocation strategy, and the annotated new samples were used to expand the original dataset with a certain proportion. The detection network was retrained with the expanded dataset. Simulation results show that the proposed framework can improve the detection efficiency and performance of the network effectively.