# Denoising Adversarial Autoencoders

arXiv: https://arxiv.org/abs/1703.01220 · HTML: https://mlsanity.com/paper/1703.01220/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2017.

## Built on by (most cited first, 20 of 20)

- [Video Summarization Using Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.06072/) (2021)
- [A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU](https://mlsanity.com/paper/2305.17473/) (2023)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [Utilizing XAI technique to improve autoencoder based model for computer network anomaly detection with shapley additive explanation(SHAP)](https://mlsanity.com/paper/2112.08442/) (2021)
- [A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks](https://mlsanity.com/paper/2102.01792/) (2021)
- [Attack and defense techniques in large language models: A survey and new perspectives](https://mlsanity.com/paper/2505.00976/) (2025)
- [Revisiting Bayesian Autoencoders with MCMC](https://mlsanity.com/paper/2104.05915/) (2021)
- [Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2205.02309/) (2022)
- [Leveraging Endo- and Exo-Temporal Regularization for Black-box Video Domain Adaptation](https://mlsanity.com/paper/2208.05187/) (2022)
- [Frequency Centric Defense Mechanisms against Adversarial Examples](https://mlsanity.com/paper/2110.13935/) (2021)
- [Learnable Faster Kernel-PCA for Nonlinear Fault Detection: Deep Autoencoder-Based Realization](https://mlsanity.com/paper/2112.04193/) (2021)
- [Survey on Visual Signal Coding and Processing with Generative Models: Technologies, Standards and Optimization](https://mlsanity.com/paper/2405.14221/) (2024)
- [FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram](https://mlsanity.com/paper/2107.07312/) (2021)
- [Robust Multimodal Fusion for Human Activity Recognition](https://mlsanity.com/paper/2303.04636/) (2023)
- [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)
- [NEMR: Network Embedding on Metric of Relation](https://mlsanity.com/paper/2101.08020/) (2021)
- [Robust DNN Surrogate Models with Uncertainty Quantification via Adversarial Training](https://mlsanity.com/paper/2211.09954/) (2022)
- [Angular triangle distance for ordinal metric learning](https://mlsanity.com/paper/2211.15200/) (2022)
- [Binary classification based Monte Carlo simulation](https://mlsanity.com/paper/2307.16035/) (2023)
- [Semiotics Networks Representing Perceptual Inference](https://mlsanity.com/paper/2310.05212/) (2023)

## Abstract (arXiv)

Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabelled input data from a latent representation space. More robust representations may be produced by an autoencoder if it learns to recover clean input samples from corrupted ones. Representations may be further improved by introducing regularisation during training to shape the distribution of the encoded data in latent space. We suggest denoising adversarial autoencoders, which combine denoising and regularisation, shaping the distribution of latent space using adversarial training. We introduce a novel analysis that shows how denoising may be incorporated into the training and sampling of adversarial autoencoders. Experiments are performed to assess the contributions that denoising makes to the learning of representations for classification and sample synthesis. Our results suggest that autoencoders trained using a denoising criterion achieve higher classification performance, and can synthesise samples that are more consistent with the input data than those trained without a corruption process.