Score-Guided Generative Adversarial Networks

by   Minhyeok Lee, et al.

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±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) of ScoreGAN trained over the CIFAR-100 dataset was 13.98.


page 4

page 6

page 12


Measures to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images

The Generative Adversarial Network (GAN) is a state-of-the-art technique...

Activation Maximization Generative Adversarial Nets

Class label information has been empirically proven to be very useful in...

Is Generator Conditioning Causally Related to GAN Performance?

Recent work (Pennington et al, 2017) suggests that controlling the entir...

Lessons Learned from the Training of GANs on Artificial Datasets

Generative Adversarial Networks (GANs) have made great progress in synth...

TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for Accurate GAN Evaluation

Evaluating image generation models such as generative adversarial networ...

ViT-Inception-GAN for Image Colourising

Studies involving colourising images has been garnering researchers' kee...

LOGAN: Latent Optimisation for Generative Adversarial Networks

Training generative adversarial networks requires balancing of delicate ...

Please sign up or login with your details

Forgot password? Click here to reset