Training Generative Adversarial Networks in One Stage

Abstract

Generative Adversarial Networks (GANs) have demonstrated unprecedented success in various image generation tasks. The encouraging results, however, come at the price of a cumbersome training process, during which the generator and discriminator are alternately updated in two stages. In this paper, we investigate a general training scheme that enables training GANs efficiently in only one stage. Based on the adversarial losses of the generator and discriminator, we categorize GANs into two classes, Symmetric GANs and Asymmetric GANs, and introduce a novel gradient decomposition method to unify the two, allowing us to train both classes in one stage and hence alleviate the training effort. We also computationally analyze the efficiency of the proposed method, and empirically demonstrate that, the proposed method yields a solid $1.5\times$ acceleration across various datasets and network architectures. Furthermore, we show that the proposed method is readily applicable to other adversarial-training scenarios, such as data-free knowledge distillation. The code is available at https://github.com/zju-vipa/OSGAN.

arXiv commentAccepted to CVPR 2021

References in corpus (20)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Distilling the Knowledge in a Neural Network
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
• Learning to Segment Object Candidates
• Large Scale Adversarial Representation Learning
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• A Note on the Inception Score
• Blind Super-Resolution Kernel Estimation using an Internal-GAN
• Demystifying MMD GANs
• Diversity-Sensitive Conditional Generative Adversarial Networks
• Boundary-Seeking Generative Adversarial Networks
• Data-Free Adversarial Distillation
• Semantic Image Inpainting with Deep Generative Models
• Progressive Network Grafting for Few-Shot Knowledge Distillation