English

Distilling Representations from GAN Generator via Squeeze and Span

Computer Vision and Pattern Recognition 2022-11-08 v1

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.

Keywords

Cite

@article{arxiv.2211.03000,
  title  = {Distilling Representations from GAN Generator via Squeeze and Span},
  author = {Yu Yang and Xiaotian Cheng and Chang Liu and Hakan Bilen and Xiangyang Ji},
  journal= {arXiv preprint arXiv:2211.03000},
  year   = {2022}
}

Comments

16 pages, NeurIPS 2022

R2 v1 2026-06-28T05:15:42.329Z