Search

We propose a novel integral probability metric-based generative adversarial network (GAN), called SphereGAN. In the proposed scheme, the distance between two probability distributions (i.e., true and fake distributions) is measured on a hypersphere. Given that its hypersphere-based objective function computes the upper bound of the distance as a half arc, SphereGAN can be stably trained and can achieve a high convergence rate. In sphereGAN, higher-order information of data is processed using multiple geometric moments, thus improving the accuracy of the distance measurement and producing more realistic outcomes. Several properties of the proposed distance metric on the hypersphere are mathematically derived. The effectiveness of the proposed SphereGAN is demonstrated through quantitative and qualitative experiments for unsupervised image generation and 3D point cloud generation, demonstrating its superiority over state-of-the-art GANs with respect to accuracy and convergence on the CIFAR-10, STL-10, LSUN bedroom, and ShapeNet datasets. [ABSTRACT FROM AUTHOR]

We propose a novel generative adversarial network for class-conditional data augmentation (i.e., GANDA) to mitigate data imbalance problems in image classification tasks. The proposed GANDA generates minority class data by exploiting majority class information to enhance the classification accuracy of minority classes. For stable GAN training, we introduce a new denoising autoencoder initialization with explicit class conditioning in the latent space, which enables the generation of definite samples. The generated samples are visually realistic and have a high resolution. Experimental results demonstrate that the proposed GANDA can considerably improve classification accuracy, especially when datasets are highly imbalanced on standard benchmark datasets (i.e., MNIST and CelebA). Our generated samples can be easily used to train conventional classifiers to enhance their classification accuracy. [ABSTRACT FROM AUTHOR]