# MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1903.06048 · HTML: https://mlsanity.com/paper/1903.06048/

## Key facts

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

## Built on by (most cited first, 14 of 14)

- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [SWAGAN: A Style-based Wavelet-driven Generative Model](https://mlsanity.com/paper/2102.06108/) (2021)
- [Generating Novel Scene Compositions from Single Images and Videos](https://mlsanity.com/paper/2103.13389/) (2021)
- [HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Images](https://mlsanity.com/paper/2103.16617/) (2021)
- [MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains](https://mlsanity.com/paper/2104.13742/) (2021)
- [DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks](https://mlsanity.com/paper/2209.07081/) (2022)
- [One-Shot Synthesis of Images and Segmentation Masks](https://mlsanity.com/paper/2209.07547/) (2022)
- [Improving Visual Representation Learning through Perceptual Understanding](https://mlsanity.com/paper/2212.14504/) (2022)
- [Diamond in the rough: Improving image realism by traversing the GAN latent space](https://mlsanity.com/paper/2104.05518/) (2021)
- [Conditional De-Identification of 3D Magnetic Resonance Images](https://mlsanity.com/paper/2110.09927/) (2021)
- [A stable deep adversarial learning approach for geological facies generation](https://mlsanity.com/paper/2305.13318/) (2023)
- [A Generative Model for Hallucinating Diverse Versions of Super Resolution Images](https://mlsanity.com/paper/2102.06624/) (2021)
- [Multi-Attributed and Structured Text-to-Face Synthesis](https://mlsanity.com/paper/2108.11100/) (2021)
- [Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis](https://mlsanity.com/paper/2303.14157/) (2023)

## Abstract (arXiv)

While Generative Adversarial Networks (GANs) have seen huge successes in image synthesis tasks, they are notoriously difficult to adapt to different datasets, in part due to instability during training and sensitivity to hyperparameters. One commonly accepted reason for this instability is that gradients passing from the discriminator to the generator become uninformative when there isn't enough overlap in the supports of the real and fake distributions. In this work, we propose the Multi-Scale Gradient Generative Adversarial Network (MSG-GAN), a simple but effective technique for addressing this by allowing the flow of gradients from the discriminator to the generator at multiple scales. This technique provides a stable approach for high resolution image synthesis, and serves as an alternative to the commonly used progressive growing technique. We show that MSG-GAN converges stably on a variety of image datasets of different sizes, resolutions and domains, as well as different types of loss functions and architectures, all with the same set of fixed hyperparameters. When compared to state-of-the-art GANs, our approach matches or exceeds the performance in most of the cases we tried.