Score-Guided Generative Adversarial Networks
This work addresses overfitting issues in GANs for image generation, offering an incremental improvement by integrating evaluation metrics as auxiliary guides.
The paper tackled the problem of overfitting in GAN training by proposing ScoreGAN, which uses pre-trained networks as evaluators to guide generator training with metrics like Inception score, achieving state-of-the-art Inception scores of 10.36±0.15 on CIFAR-10 and an FID of 13.98 on CIFAR-100.
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.