# Improved Training with Curriculum GANs

arXiv: https://arxiv.org/abs/1807.09295 · HTML: https://mlsanity.com/paper/1807.09295/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 4 of 4)

- [Learning Category-Level Generalizable Object Manipulation Policy via Generative Adversarial Self-Imitation Learning from Demonstrations](https://mlsanity.com/paper/2203.02107/) (2022)
- [Exploring Dropout Discriminator for Domain Adaptation](https://mlsanity.com/paper/2107.04231/) (2021)
- [ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation](https://mlsanity.com/paper/2404.07564/) (2024)
- [CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning](https://mlsanity.com/paper/2504.16364/) (2025)

## Abstract (arXiv)

In this paper we introduce Curriculum GANs, a curriculum learning strategy for training Generative Adversarial Networks that increases the strength of the discriminator over the course of training, thereby making the learning task progressively more difficult for the generator. We demonstrate that this strategy is key to obtaining state-of-the-art results in image generation. We also show evidence that this strategy may be broadly applicable to improving GAN training in other data modalities.