Score-Guided Generative Adversarial Networks
arXiv:2004.04396
Abstract
We propose a Generative Adversarial Network (GAN) that introduces an evaluator module using pre-trained networks. The proposed model, called score-guided GAN (ScoreGAN), is trained with an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of the generator. By using another pre-trained network instead of the Inception network, ScoreGAN circumvents the overfitting of the Inception network in order that generated samples do not correspond to adversarial examples of the Inception network. Also, to prevent the overfitting, the evaluation metrics are employed only as an auxiliary role, while the conventional target of GANs is mainly used. Evaluated with the CIFAR-10 dataset, ScoreGAN demonstrated an Inception score of 10.360.15, which corresponds to state-of-the-art performance. Furthermore, to generalize the effectiveness of ScoreGAN, the model was further evaluated with another dataset, i.e., the CIFAR-100; as a result, ScoreGAN outperformed the other existing methods, where the Fréchet Inception Distance (FID) was 13.98.
References in corpus (15)
- Generative Adversarial Networks: An Overview
- 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
- Self-Attention Generative Adversarial Networks
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Generative Adversarial Network in Medical Imaging: A Review
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- A Learned Representation For Artistic Style
- A Note on the Inception Score
- Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
- Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
- Class-Splitting Generative Adversarial Networks
- Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies
- cGANs with Multi-Hinge Loss