Information-Theoretic GAN Compression with Variational Energy-based ModelDownload PDF

Published: 31 Oct 2022, Last Modified: 14 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: GAN Compression, Knowledge Distillation, Mutual Information
TL;DR: 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.
Abstract: 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.
Supplementary Material: zip
16 Replies

Loading