English

Improved Input Reprogramming for GAN Conditioning

Machine Learning 2022-02-08 v3 Artificial Intelligence

Abstract

We study the GAN conditioning problem, whose goal is to convert a pretrained unconditional GAN into a conditional GAN using labeled data. We first identify and analyze three approaches to this problem -- conditional GAN training from scratch, fine-tuning, and input reprogramming. Our analysis reveals that when the amount of labeled data is small, input reprogramming performs the best. Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm. After identifying a few critical issues of the previous input reprogramming approach, we propose a new algorithm called InRep+. Our algorithm InRep+ addresses the existing issues with the novel uses of invertible neural networks and Positive-Unlabeled (PU) learning. Via extensive experiments, we show that InRep+ outperforms all existing methods, particularly when label information is scarce, noisy, and/or imbalanced. For instance, for the task of conditioning a CIFAR10 GAN with 1% labeled data, InRep+ achieves an average Intra-FID of 76.24, whereas the second-best method achieves 114.51.

Keywords

Cite

@article{arxiv.2201.02692,
  title  = {Improved Input Reprogramming for GAN Conditioning},
  author = {Tuan Dinh and Daewon Seo and Zhixu Du and Liang Shang and Kangwook Lee},
  journal= {arXiv preprint arXiv:2201.02692},
  year   = {2022}
}

Comments

24 pages, 7 figures

R2 v1 2026-06-24T08:43:21.495Z