# Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training

arXiv: https://arxiv.org/abs/1906.01984 · HTML: https://mlsanity.com/paper/1906.01984/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [NWT: Towards natural audio-to-video generation with representation learning](https://mlsanity.com/paper/2106.04283/) (2021)
- [FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features](https://mlsanity.com/paper/2404.09736/) (2024)
- [GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning](https://mlsanity.com/paper/2402.02003/) (2024)
- [Gromov-Wasserstein Autoencoders](https://mlsanity.com/paper/2209.07007/) (2022)
- [A multimodal dynamical variational autoencoder for audiovisual speech representation learning](https://mlsanity.com/paper/2305.03582/) (2023)
- [Data Assimilation Predictive GAN (DA-PredGAN): applied to determine the spread of COVID-19](https://mlsanity.com/paper/2105.07729/) (2021)
- [Hyper-Transforming Latent Diffusion Models](https://mlsanity.com/paper/2504.16580/) (2025)
- [Achieving Explainability for Plant Disease Classification with Disentangled Variational Autoencoders](https://mlsanity.com/paper/2102.03082/) (2021)
- [Deep clustering with fusion autoencoder](https://mlsanity.com/paper/2201.04727/) (2022)
- [Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI](https://mlsanity.com/paper/2412.00511/) (2024)
- [Generative Adversarial Networks for High-Dimensional Item Factor Analysis: A Deep Adversarial Learning Algorithm](https://mlsanity.com/paper/2502.10650/) (2025)
- [RENs: Relevance Encoding Networks](https://mlsanity.com/paper/2205.13061/) (2022)

## Abstract (arXiv)

We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force the VAE to output realistic and natural images. We present experimental results to show that the VAE trained with our new method outperforms state of the art in generating face images with much clearer and more natural noses, eyes, teeth, hair textures as well as reasonable backgrounds. We also show that our method can learn powerful embeddings of input face images, which can be used to achieve facial attribute manipulation. Moreover we propose a multi-view feature extraction strategy to extract effective image representations, which can be used to achieve state of the art performance in facial attribute prediction.