# Dual Adversarial Auto-Encoders for Clustering

arXiv: https://arxiv.org/abs/2008.10038 · HTML: https://mlsanity.com/paper/2008.10038/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

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

- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Unsupervised Continual Learning in Streaming Environments](https://mlsanity.com/paper/2109.09282/) (2021)
- [Learning Disentangled Representations for Generalized Multi-view Clustering](https://mlsanity.com/paper/2605.15640/) (2026)
- [FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram](https://mlsanity.com/paper/2107.07312/) (2021)
- [Label Assisted Autoencoder for Anomaly Detection in Power Generation Plants](https://mlsanity.com/paper/2302.02896/) (2023)
- [Robust DNN Surrogate Models with Uncertainty Quantification via Adversarial Training](https://mlsanity.com/paper/2211.09954/) (2022)
- [Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks](https://mlsanity.com/paper/2212.01521/) (2022)

## Abstract (arXiv)

As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been developed, but most of them perform unsatisfactorily on the data with complex structures. Recently, Adversarial Auto-Encoder (AAE) shows effectiveness on tackling such data by combining Auto-Encoder (AE) and adversarial training, but it cannot effectively extract classification information from the unlabeled data. In this work, we propose Dual Adversarial Auto-encoder (Dual-AAE) which simultaneously maximizes the likelihood function and mutual information between observed examples and a subset of latent variables. By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders. Moreover, to avoid mode collapse, we introduce the clustering regularization term for the category variable. Experiments on four benchmarks show that Dual-AAE achieves superior performance over state-of-the-art clustering methods. Besides, by adding a reject option, the clustering accuracy of Dual-AAE can reach that of supervised CNN algorithms. Dual-AAE can also be used for disentangling style and content of images without using supervised information.