# Adaptive Density Estimation for Generative Models

arXiv: https://arxiv.org/abs/1901.01091 · HTML: https://mlsanity.com/paper/1901.01091/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2019.

## Built on by (most cited first, 16 of 16)

- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting](https://mlsanity.com/paper/2210.10542/) (2022)
- [Densely connected normalizing flows](https://mlsanity.com/paper/2106.04627/) (2021)
- [DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition](https://mlsanity.com/paper/2207.02606/) (2022)
- [On Advantages of Mask-level Recognition for Outlier-aware Segmentation](https://mlsanity.com/paper/2301.03407/) (2023)
- [Outlier detection by ensembling uncertainty with negative objectness](https://mlsanity.com/paper/2402.15374/) (2024)
- [Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection](https://mlsanity.com/paper/2302.07106/) (2023)
- [Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data](https://mlsanity.com/paper/2112.12833/) (2021)
- [Diversity vs. Recognizability: Human-like generalization in one-shot generative models](https://mlsanity.com/paper/2205.10370/) (2022)
- [Estimating the Completeness of Discrete Speech Units](https://mlsanity.com/paper/2409.06109/) (2024)
- [Hybrid Open-set Segmentation with Synthetic Negative Data](https://mlsanity.com/paper/2301.08555/) (2023)
- [Unlocking Pre-trained Image Backbones for Semantic Image Synthesis](https://mlsanity.com/paper/2312.13314/) (2023)
- [Purposer: Putting Human Motion Generation in Context](https://mlsanity.com/paper/2404.12942/) (2024)
- [Synthesising Activity Participations and Scheduling with Deep Generative Machine Learning](https://mlsanity.com/paper/2501.10221/) (2025)
- [Intriguing Properties of Modern GANs](https://mlsanity.com/paper/2402.14098/) (2024)
- [Black box behavioural modelling: Predicting human activity schedules with a deep conditional generative approach](https://mlsanity.com/paper/2512.04223/) (2025)

## Abstract (arXiv)

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample quality, but suffer from two drawbacks: (i) they mode-drop, i.e., do not cover the full support of the train data, and (ii) they do not allow for likelihood evaluations on held-out data. In contrast, likelihood-based training encourages models to cover the full support of the train data, but yields poorer samples. These mutual shortcomings can in principle be addressed by training generative latent variable models in a hybrid adversarial-likelihood manner. However, we show that commonly made parametric assumptions create a conflict between them, making successful hybrid models non trivial. As a solution, we propose to use deep invertible transformations in the latent variable decoder. This approach allows for likelihood computations in image space, is more efficient than fully invertible models, and can take full advantage of adversarial training. We show that our model significantly improves over existing hybrid models: offering GAN-like samples, IS and FID scores that are competitive with fully adversarial models, and improved likelihood scores.