# It Takes (Only) Two: Adversarial Generator-Encoder Networks

arXiv: https://arxiv.org/abs/1704.02304 · HTML: https://mlsanity.com/paper/1704.02304/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2017.

## Built on by (most cited first, 19 of 19)

- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [Conditional Invertible Neural Networks for Diverse Image-to-Image Translation](https://mlsanity.com/paper/2105.02104/) (2021)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)
- [Inferential Wasserstein Generative Adversarial Networks](https://mlsanity.com/paper/2109.05652/) (2021)
- [Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning](https://mlsanity.com/paper/2303.13133/) (2023)
- [Matching aggregate posteriors in the variational autoencoder](https://mlsanity.com/paper/2311.07693/) (2023)
- [Learning beyond sensations: how dreams organize neuronal representations](https://mlsanity.com/paper/2308.01830/) (2023)
- [One-shot domain adaptation for semantic face editing of real world images using StyleALAE](https://mlsanity.com/paper/2108.13876/) (2021)
- [IGAN: Inferent and Generative Adversarial Networks](https://mlsanity.com/paper/2109.13360/) (2021)
- [A Bayesian Non-parametric Approach to Generative Models: Integrating Variational Autoencoder and Generative Adversarial Networks using Wasserstein and Maximum Mean Discrepancy](https://mlsanity.com/paper/2308.14048/) (2023)
- [NeurInt : Learning to Interpolate through Neural ODEs](https://mlsanity.com/paper/2111.04123/) (2021)
- [Autoencoding Video Latents for Adversarial Video Generation](https://mlsanity.com/paper/2201.06888/) (2022)
- [Deep Learning to Jointly Schema Match, Impute, and Transform Databases](https://mlsanity.com/paper/2207.03536/) (2022)
- [Conditioning Generative Latent Optimization for Sparse-View CT Image Reconstruction](https://mlsanity.com/paper/2307.16670/) (2023)
- [Deep Learning for Video-Based Assessment of Endotracheal Intubation Skills](https://mlsanity.com/paper/2404.11727/) (2024)
- [SwinStyleformer is a favorable choice for image inversion](https://mlsanity.com/paper/2406.13153/) (2024)

## Abstract (arXiv)

We present a new autoencoder-type architecture that is trainable in an unsupervised mode, sustains both generation and inference, and has the quality of conditional and unconditional samples boosted by adversarial learning. Unlike previous hybrids of autoencoders and adversarial networks, the adversarial game in our approach is set up directly between the encoder and the generator, and no external mappings are trained in the process of learning. The game objective compares the divergences of each of the real and the generated data distributions with the prior distribution in the latent space. We show that direct generator-vs-encoder game leads to a tight coupling of the two components, resulting in samples and reconstructions of a comparable quality to some recently-proposed more complex architectures.