A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
This work addresses the problem of understanding and enhancing generative capabilities in robust machine learning models for researchers in adversarial and generative AI, offering a novel theoretical framework with practical improvements.
The paper tackles the unexplained generative ability of adversarially trained models by developing a unified probabilistic framework called Contrastive Energy-based Models (CEM), which interprets adversarial training and unsupervised contrastive learning, leading to improved sampling methods that achieve an Inception score of 9.61 on CIFAR-10.
Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers notice that robust models with AT have good generative ability and can synthesize realistic images, while the reason behind it is yet under-explored. In this paper, we demystify this phenomenon by developing a unified probabilistic framework, called Contrastive Energy-based Models (CEM). On the one hand, we provide the first probabilistic characterization of AT through a unified understanding of robustness and generative ability. On the other hand, our unified framework can be extended to the unsupervised scenario, which interprets unsupervised contrastive learning as an important sampling of CEM. Based on these, we propose a principled method to develop adversarial learning and sampling methods. Experiments show that the sampling methods derived from our framework improve the sample quality in both supervised and unsupervised learning. Notably, our unsupervised adversarial sampling method achieves an Inception score of 9.61 on CIFAR-10, which is superior to previous energy-based models and comparable to state-of-the-art generative models.