摘要
在图像识别领域,针对有监督方法的模型在标签数据不足时图像的识别效果不佳问题,提出一种基于生成对抗网络(GAN)的半监督方法模型,即结合了半监督生成对抗网络(SSGAN)和深度卷积生成对抗网络(DCGAN)的优点,并在输出层用softmax代替了sigmoid激活函数,从而建立半监督深度卷积生成对抗网络(SS-DCGAN)模型。首先,将生成样本定义为伪样本类别并用于引导训练;其次,采用半监督的训练方式对模型的参数进行更新;最后,实现对异常(脑梗死)图像的识别。实验结果表明,SS-DCGAN模型在标签数据较少时能够很好地识别异常图像,达到95.05%的识别率,与ResNet32、半监督梯度网络(Ladder Network)分类方法相比具有显著的优越性。
In the field of image recognition,images with insufficient label data cannot be well recognized by the supervised method model.In order to solve this problem,a semi-supervised method model based on Generative Adversarial Network(GAN)was proposed.That is,by combining the advantages of semi-supervised GANs and deep convolutional GANs,and replacing the sigmoid activation function with softmax in the output layer,the Semi-Supervised Deep Convolutional GAN(SS-DCGAN)model was established.Firstly,the generated samples were defined as pseudo-samples and used to guide the training process.Secondly,the semi-supervised training method was adopted to update the parameters of the model.Finally,the recognition of abnormal(cerebral infarction)images was realized.Experimental results show that the SS-DCGAN model can recognize abnormal images well with little label data,which achieves 95.05%recognition rates.Compared with Residual Network 32(ResNet32)and Ladder networks,the SS-DCGAN model has significant advantages.
作者
欧莉莉
邵峰晶
孙仁诚
隋毅
OU Lili;SHAO Fengjing;SUN Rencheng;SUI Yi(College of Computer Science and Technology,Qingdao University,Qingdao Shandong 266071,China;The Affiliated Hospital of Qingdao University,Qingdao Shandong 266071,China)
出处
《计算机应用》
CSCD
北大核心
2021年第4期1221-1226,共6页
journal of Computer Applications
基金
国家自然科学基金青年科学基金资助项目(41706198)。
关键词
生成对抗网络
半监督
脑梗
深度卷积网络
图像识别
特征匹配
Generative Adversarial Network(GAN)
semi-supervised
cerebral infarction
deep convolutional networks
image recognition
feature matching
