# AVAE: Adversarial Variational Auto Encoder

arXiv: https://arxiv.org/abs/2012.11551 · HTML: https://mlsanity.com/paper/2012.11551/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Can Your Generative Model Detect Out-of-Distribution Covariate Shift?](https://mlsanity.com/paper/2409.03043/) (2024)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)
- [Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent Space](https://mlsanity.com/paper/2305.12906/) (2023)
- [DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection](https://mlsanity.com/paper/2501.08005/) (2025)
- [Compressed representation of brain genetic transcription](https://mlsanity.com/paper/2310.16113/) (2023)
- [AdverX-Ray: Ensuring X-Ray Integrity Through Frequency-Sensitive Adversarial VAEs](https://mlsanity.com/paper/2502.16610/) (2025)

## Abstract (arXiv)

Among the wide variety of image generative models, two models stand out: Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). GANs can produce realistic images, but they suffer from mode collapse and do not provide simple ways to get the latent representation of an image. On the other hand, VAEs do not have these problems, but they often generate images less realistic than GANs. In this article, we explain that this lack of realism is partially due to a common underestimation of the natural image manifold dimensionality. To solve this issue we introduce a new framework that combines VAE and GAN in a novel and complementary way to produce an auto-encoding model that keeps VAEs properties while generating images of GAN-quality. We evaluate our approach both qualitatively and quantitatively on five image datasets.