# Investigating Shifts in GAN Output-Distributions

arXiv: https://arxiv.org/abs/2112.14061 · HTML: https://mlsanity.com/paper/2112.14061/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 28 Dec 2021.

## Builds on (most cited first, 13 of 13)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications](https://mlsanity.com/paper/2001.06937/) (2020)
- [Self-Supervised GANs via Auxiliary Rotation Loss](https://mlsanity.com/paper/1811.11212/) (2018)
- [InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning](https://mlsanity.com/paper/2007.04589/) (2020)
- [Spectral Distribution Aware Image Generation](https://mlsanity.com/paper/2012.03110/) (2020)
- [Some Theoretical Properties of GANs](https://mlsanity.com/paper/1803.07819/) (2018)
- [Mimicry: Towards the Reproducibility of GAN Research](https://mlsanity.com/paper/2005.02494/) (2020)

## Abstract (arXiv)

A fundamental and still largely unsolved question in the context of Generative Adversarial Networks is whether they are truly able to capture the real data distribution and, consequently, to sample from it. In particular, the multidimensional nature of image distributions leads to a complex evaluation of the diversity of GAN distributions. Existing approaches provide only a partial understanding of this issue, leaving the question unanswered. In this work, we introduce a loop-training scheme for the systematic investigation of observable shifts between the distributions of real training data and GAN generated data. Additionally, we introduce several bounded measures for distribution shifts, which are both easy to compute and to interpret. Overall, the combination of these methods allows an explorative investigation of innate limitations of current GAN algorithms. Our experiments on different data-sets and multiple state-of-the-art GAN architectures show large shifts between input and output distributions, showing that existing theoretical guarantees towards the convergence of output distributions appear not to be holding in practice.