Adversarial Autoencoders Oversampling Algorithm for Imbalanced Image Data
Many traditional imbalanced learning algorithms suitable for low-dimensional data do not perform well on image data.Although the oversampling algorithm based on Generative Adversarial Networks(GAN)can generate high-quality images,it is prone to mode collapse in the case of class imbalance.Oversampling algorithms based on AutoEncoders(AE)are easy to train,but the generated images are of lower quality.In order to improve the quality of samples generated by the oversampling algorithm in imbalanced images and the stability of training,a Balanced oversampling method with AutoEncoders and Generative Adversarial Networks(BAEGAN)is proposed in this paper,which is based on the idea of GAN and AE.First,a conditional embedding layer is introduced in the Autoencoder,and the pre-trained conditional Autoencoder is used to initialize the GAN to stabilize the model training;then the output structure of the discriminator is improved,and a loss function that combines Focal Loss and gradient penalty is proposed to alleviate the impact of class imbalance;and finally the Synthetic Minority Oversampling TEchnique(SMOTE)is used to generate high-quality images from the distribution map of latent vectors.Experimental results on four image data sets show that the proposed algorithm is superior to oversampling methods such as Auxiliary Classifier Generative Adversarial Networks(ACGAN)and BAlancing Generative Adversarial Networks(BAGAN)in terms of image quality and classification performance after oversampling and can effectively solve the class imbalance problem in image data.
万方数据
维普
