# Transforming the output of GANs by fine-tuning them with features from different datasets

arXiv: https://arxiv.org/abs/1910.02411 · HTML: https://mlsanity.com/paper/1910.02411/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Oct 2019.

## Built on by (most cited first, 2 of 2)

- [Active Divergence with Generative Deep Learning -- A Survey and Taxonomy](https://mlsanity.com/paper/2107.05599/) (2021)
- [Discriminator Synthesis: On reusing the other half of Generative Adversarial Networks](https://mlsanity.com/paper/2111.02175/) (2021)

## Abstract (arXiv)

In this work we present a method for fine-tuning pre-trained GANs with features from different datasets, resulting in the transformation of the output distribution into a new distribution with novel characteristics. The weights of the generator are updated using the weighted sum of the losses from a cross-dataset classifier and the frozen weights of the pre-trained discriminator. We discuss details of the technical implementation and share some of the visual results from this training process.