Distilling Representations from GAN Generator via Squeeze and Span

TL;DR

This paper introduces a novel method to distill and transfer GAN generator representations into a student network using squeezing and spanning techniques, improving real domain performance and aiding self-supervised learning.

Contribution

It proposes a new approach to extract and transfer informative GAN representations to downstream tasks, addressing mode collapse and enhancing real data performance.

Findings

Effective in transferring GAN features to downstream tasks

Improves performance on real domain data

Enhances self-supervised representation learning

Abstract

In recent years, generative adversarial networks (GANs) have been an actively studied topic and shown to successfully produce high-quality realistic images in various domains. The controllable synthesis ability of GAN generators suggests that they maintain informative, disentangled, and explainable image representations, but leveraging and transferring their representations to downstream tasks is largely unexplored. In this paper, we propose to distill knowledge from GAN generators by squeezing and spanning their representations. We squeeze the generator features into representations that are invariant to semantic-preserving transformations through a network before they are distilled into the student network. We span the distilled representation of the synthetic domain to the real domain by also using real training data to remedy the mode collapse of GANs and boost the student network performance in a real domain. Experiments justify the efficacy of our method and reveal its great significance in self-supervised representation learning. Code is available at https://github.com/yangyu12/squeeze-and-span.