论文标题
得分引导的生成对抗网络
Score-Guided Generative Adversarial Networks
论文作者
论文摘要
我们提出了一个生成对抗网络（GAN），该网络使用预训练的网络介绍了评估器模块。所提出的称为得分引导GAN（SCOREGAN）的模型对GAN的评估度量进行了训练，即Inception评分，作为发电机训练的粗略指南。通过使用另一个预先训练的网络而不是成立网络，ScoreGan绕过了启动网络的过度拟合，以使生成的样本与启动网络的对抗性示例相对应。同样，为了防止过度拟合，评估指标仅作为辅助作用，而gan的常规目标主要使用。 ScoreGan通过CIFAR-10数据集进行评估，其成立分数为10.36 $ \ pm $ 0.15，这与最先进的性能相对应。此外，为了概括得分的有效性，该模型通过另一个数据集进一步评估，即CIFAR-100；结果，得分gan的表现优于其他现有方法，其中fréchet成立距离（FID）为13.98。
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 10.36$\pm$0.15, 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.
