# TinyGAN: Distilling BigGAN for Conditional Image Generation

Source: [TinyGAN: Distilling BigGAN for Conditional Image Generation](<https://www.sota2.com/research/paper/68fa68651e209131cea1bc32>)

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

Data updated: 2025-10-25T22:36:00.183Z

Authors: Ting-Yun Chang, Chi-Jen Lu

Published: 2020-09-29T07:33:49.000Z

## Abstract

Generative Adversarial Networks (GANs) have become a powerful approach for generative image modeling. However, GANs are notorious for their training instability, especially on large-scale, complex datasets. While the recent work of BigGAN has significantly improved the quality of image generation on ImageNet, it requires a huge model, making it hard to deploy on resource-constrained devices. To reduce the model size, we propose a black-box knowledge distillation framework for compressing GANs, which highlights a stable and efficient training process. Given BigGAN as the teacher network, we manage to train a much smaller student network to mimic its functionality, achieving competitive performance on Inception and FID scores with the generator having $16\\times$ fewer parameters.

## 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/2009.13829>)

[PDF](<https://arxiv.org/pdf/2009.13829.pdf>)