# Beyond the Known: Adversarial Autoencoders in Novelty Detection

arXiv: https://arxiv.org/abs/2404.04456 · HTML: https://mlsanity.com/paper/2404.04456/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 6 Apr 2024.

## Builds on (most cited first, 27 of 27)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [Learning Temporal Regularity in Video Sequences](https://mlsanity.com/paper/1604.04574/) (2016)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Adversarially Learned One-Class Classifier for Novelty Detection](https://mlsanity.com/paper/1802.09088/) (2018)
- [Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video](https://mlsanity.com/paper/1812.04960/) (2018)
- [Generative Probabilistic Novelty Detection with Adversarial Autoencoders](https://mlsanity.com/paper/1807.02588/) (2018)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Learning Deep Representations of Appearance and Motion for Anomalous Event Detection](https://mlsanity.com/paper/1510.01553/) (2015)
- [Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection](https://mlsanity.com/paper/2203.02194/) (2022)
- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge](https://mlsanity.com/paper/1709.09121/) (2017)
- [SoftPatch: Unsupervised Anomaly Detection with Noisy Data](https://mlsanity.com/paper/2403.14233/) (2024)
- [Plug-and-Play CNN for Crowd Motion Analysis: An Application in Abnormal Event Detection](https://mlsanity.com/paper/1610.00307/) (2016)
- [Dual Principal Component Pursuit](https://mlsanity.com/paper/1510.04390/) (2015)
- [Provable Self-Representation Based Outlier Detection in a Union of Subspaces](https://mlsanity.com/paper/1704.03925/) (2017)
- [PixelGAN Autoencoders](https://mlsanity.com/paper/1706.00531/) (2017)
- [Coherence Pursuit: Fast, Simple, and Robust Principal Component Analysis](https://mlsanity.com/paper/1609.04789/) (2016)
- [Robust Kernel Density Estimation with Median-of-Means principle](https://mlsanity.com/paper/2006.16590/) (2020)

## Built on by (most cited first, 1 of 1)

- [Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey](https://mlsanity.com/paper/2511.05982/) (2025)

## Abstract (arXiv)

In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with a lightweight deep network, and we adopt a probabilistic score with reconstruction error. Our methodology calculates the probability of whether the sample comes from the inlier distribution or not. This work makes two key contributions. The first is that we compute the novelty probability by linearizing the manifold that holds the structure of the inlier distribution. This allows us to interpret how the probability is distributed and can be determined in relation to the local coordinates of the manifold tangent space. The second contribution is that we improve the training protocol for the network. Our results indicate that our approach is effective at learning the target class, and it outperforms recent state-of-the-art methods on several benchmark datasets.