# A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings

Source: [A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings](<https://www.sota2.com/research/paper/68fa68811e209131cea1c8a3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:44.875Z

Authors: Qi Li, Long Mai, Michael A. Alcorn, Anh Nguyen

Published: 2019-10-10T15:18:28.000Z

## Abstract

Large, pre-trained generative models have been increasingly popular and useful to both the research and wider communities. Specifically, BigGANs a class-conditional Generative Adversarial Networks trained on ImageNet---achieved excellent, state-of-the-art capability in generating realistic photos. However, fine-tuning or training BigGANs from scratch is practically impossible for most researchers and engineers because (1) GAN training is often unstable and suffering from mode-collapse; and (2) the training requires a significant amount of computation, 256 Google TPUs for 2 days or 8xV100 GPUs for 15 days. Importantly, many pre-trained generative models both in NLP and image domains were found to contain biases that are harmful to society. Thus, we need computationally-feasible methods for modifying and re-purposing these huge, pre-trained models for downstream tasks. In this paper, we propose a cost-effective optimization method for improving and re-purposing BigGANs by fine-tuning only the class-embedding layer. We show the effectiveness of our model-editing approach in three tasks: (1) significantly improving the realism and diversity of samples of complete mode-collapse classes; (2) re-purposing ImageNet BigGANs for generating images for Places365; and (3) de-biasing or improving the sample diversity for selected ImageNet classes.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.04760>)

[PDF](<https://arxiv.org/pdf/1910.04760.pdf>)