Scalable Balanced Training of Conditional Generative Adversarial Neural Networks on Image Data
This work addresses scalability and imbalance issues in training conditional GANs for image generation, which is an incremental improvement over existing methods.
The paper tackles the problem of training deep convolutional generative adversarial neural networks (DC-CGANs) more efficiently by proposing a distributed method that reduces generator-discriminator imbalance and enhances scalability through parallel training of multiple generators, showing significant improvements in inception score and image quality on MNIST, CIFAR10, CIFAR100, and ImageNet1k datasets compared to state-of-the-art techniques.
We propose a distributed approach to train deep convolutional generative adversarial neural network (DC-CGANs) models. Our method reduces the imbalance between generator and discriminator by partitioning the training data according to data labels, and enhances scalability by performing a parallel training where multiple generators are concurrently trained, each one of them focusing on a single data label. Performance is assessed in terms of inception score and image quality on MNIST, CIFAR10, CIFAR100, and ImageNet1k datasets, showing a significant improvement in comparison to state-of-the-art techniques to training DC-CGANs. Weak scaling is attained on all the four datasets using up to 1,000 processes and 2,000 NVIDIA V100 GPUs on the OLCF supercomputer Summit.