Improving Model Compatibility of Generative Adversarial Networks by Boundary Calibration

by   Si-An Chen, et al.

Generative Adversarial Networks (GANs) is a powerful family of models that learn an underlying distribution to generate synthetic data. Many existing studies of GANs focus on improving the realness of the generated image data for visual applications, and few of them concern about improving the quality of the generated data for training other classifiers – a task known as the model compatibility problem. As a consequence, existing GANs often prefer generating `easier' synthetic data that are far from the boundaries of the classifiers, and refrain from generating near-boundary data, which are known to play an important roles in training the classifiers. To improve GAN in terms of model compatibility, we propose Boundary-Calibration GANs (BCGANs), which leverage the boundary information from a set of pre-trained classifiers using the original data. In particular, we introduce an auxiliary Boundary-Calibration loss (BC-loss) into the generator of GAN to match the statistics between the posterior distributions of original data and generated data with respect to the boundaries of the pre-trained classifiers. The BC-loss is provably unbiased and can be easily coupled with different GAN variants to improve their model compatibility. Experimental results demonstrate that BCGANs not only generate realistic images like original GANs but also achieves superior model compatibility than the original GANs.


VARGAN: Variance Enforcing Network Enhanced GAN

Generative adversarial networks (GANs) are one of the most widely used g...

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

We present an approach to quantifying both aleatoric and epistemic uncer...

Data Synthesis based on Generative Adversarial Networks

Privacy is an important concern for our society where sharing data with ...

Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary

Generative models, such as Generative Adversarial Networks (GANs), have ...

Protecting GANs against privacy attacks by preventing overfitting

Generative Adversarial Networks (GANs) have made releasing of synthetic ...

CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis

Generative adversarial networks (GANs) have drawn considerable attention...

A Method for Evaluating the Capacity of Generative Adversarial Networks to Reproduce High-order Spatial Context

Generative adversarial networks are a kind of deep generative model with...

Please sign up or login with your details

Forgot password? Click here to reset