Information-Theoretic GAN Compression with Variational Energy-based Model
This work addresses the need for efficient model compression in GANs, which is incremental as it builds on existing knowledge distillation methods by incorporating an energy-based model for better optimization.
The paper tackles the problem of compressing generative adversarial networks (GANs) by proposing an information-theoretic knowledge distillation approach that maximizes mutual information between teacher and student networks using a variational optimization based on an energy-based model, achieving outstanding performance in model compression consistently across several existing models.
We propose an information-theoretic knowledge distillation approach for the compression of generative adversarial networks, which aims to maximize the mutual information between teacher and student networks via a variational optimization based on an energy-based model. Because the direct computation of the mutual information in continuous domains is intractable, our approach alternatively optimizes the student network by maximizing the variational lower bound of the mutual information. To achieve a tight lower bound, we introduce an energy-based model relying on a deep neural network to represent a flexible variational distribution that deals with high-dimensional images and consider spatial dependencies between pixels, effectively. Since the proposed method is a generic optimization algorithm, it can be conveniently incorporated into arbitrary generative adversarial networks and even dense prediction networks, e.g., image enhancement models. We demonstrate that the proposed algorithm achieves outstanding performance in model compression of generative adversarial networks consistently when combined with several existing models.