# AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation

arXiv: https://arxiv.org/abs/1812.05796 · HTML: https://mlsanity.com/paper/1812.05796/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows](https://mlsanity.com/paper/2101.05796/) (2021)
- [Flow-based Self-supervised Density Estimation for Anomalous Sound Detection](https://mlsanity.com/paper/2103.08801/) (2021)
- [Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning](https://mlsanity.com/paper/2112.02922/) (2021)
- [Robust Audio Anomaly Detection](https://mlsanity.com/paper/2202.01784/) (2022)
- [Learning to Adapt to Domain Shifts with Few-shot Samples in Anomalous Sound Detection](https://mlsanity.com/paper/2204.01905/) (2022)
- [Anomalous Sound Detection Based on Machine Activity Detection](https://mlsanity.com/paper/2204.07353/) (2022)
- [Zero-shot domain adaptation of anomalous samples for semi-supervised anomaly detection](https://mlsanity.com/paper/2304.02221/) (2023)

## Abstract (arXiv)

We tackle unsupervised anomaly detection (UAD), a problem of detecting data that significantly differ from normal data. UAD is typically solved by using density estimation. Recently, deep neural network (DNN)-based density estimators, such as Normalizing Flows, have been attracting attention. However, one of their drawbacks is the difficulty in adapting them to the change in the normal data's distribution. To address this difficulty, we propose AdaFlow, a new DNN-based density estimator that can be easily adapted to the change of the distribution. AdaFlow is a unified model of a Normalizing Flow and Adaptive Batch-Normalizations, a module that enables DNNs to adapt to new distributions. AdaFlow can be adapted to a new distribution by just conducting forward propagation once per sample; hence, it can be used on devices that have limited computational resources. We have confirmed the effectiveness of the proposed model through an anomaly detection in a sound task. We also propose a method of applying AdaFlow to the unpaired cross-domain translation problem, in which one has to train a cross-domain translation model with only unpaired samples. We have confirmed that our model can be used for the cross-domain translation problem through experiments on image datasets.