# Neural Transformation Learning for Deep Anomaly Detection Beyond Images

arXiv: https://arxiv.org/abs/2103.16440 · HTML: https://mlsanity.com/paper/2103.16440/

## Key facts

- Cited by 99 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 62 references that are in the map.
- First posted on arXiv 30 Mar 2021.

## Builds on (most cited first, 30 of 34)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [The UEA multivariate time series classification archive, 2018](https://mlsanity.com/paper/1811.00075/) (2018)
- [On Mutual Information Maximization for Representation Learning](https://mlsanity.com/paper/1907.13625/) (2019)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Fast AutoAugment](https://mlsanity.com/paper/1905.00397/) (2019)
- [Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction](https://mlsanity.com/paper/1611.09842/) (2016)
- [LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection](https://mlsanity.com/paper/1607.00148/) (2016)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules](https://mlsanity.com/paper/1905.05393/) (2019)
- [Latent Space Autoregression for Novelty Detection](https://mlsanity.com/paper/1807.01653/) (2018)
- [Benchmarking Multivariate Time Series Classification Algorithms](https://mlsanity.com/paper/2007.13156/) (2020)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Adversarial AutoAugment](https://mlsanity.com/paper/1912.11188/) (2019)
- [Learning to Compose Domain-Specific Transformations for Data Augmentation](https://mlsanity.com/paper/1709.01643/) (2017)
- [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders](https://mlsanity.com/paper/1806.04972/) (2018)

## Built on by (most cited first, 30 of 99)

- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [Latent Outlier Exposure for Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2202.08088/) (2022)
- [Raising the Bar in Graph-level Anomaly Detection](https://mlsanity.com/paper/2205.13845/) (2022)
- [Calibrated One-class Classification for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2207.12201/) (2022)
- [Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning](https://mlsanity.com/paper/2305.16114/) (2023)
- [Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook](https://mlsanity.com/paper/2205.05173/) (2022)
- [Perturbation Learning Based Anomaly Detection](https://mlsanity.com/paper/2206.02704/) (2022)
- [Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution](https://mlsanity.com/paper/2206.07647/) (2022)
- [Graph Anomaly Detection with Graph Neural Networks: Current Status and Challenges](https://mlsanity.com/paper/2209.14930/) (2022)
- [Beyond Individual Input for Deep Anomaly Detection on Tabular Data](https://mlsanity.com/paper/2305.15121/) (2023)
- [Data-Efficient and Interpretable Tabular Anomaly Detection](https://mlsanity.com/paper/2203.02034/) (2022)
- [Anomaly Detection Requires Better Representations](https://mlsanity.com/paper/2210.10773/) (2022)
- [Set Features for Fine-grained Anomaly Detection](https://mlsanity.com/paper/2302.12245/) (2023)
- [Detecting Anomalies within Time Series using Local Neural Transformations](https://mlsanity.com/paper/2202.03944/) (2022)
- [A Revealing Large-Scale Evaluation of Unsupervised Anomaly Detection Algorithms](https://mlsanity.com/paper/2204.09825/) (2022)
- [Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success](https://mlsanity.com/paper/2208.07734/) (2022)
- [Contrastive Predictive Coding for Anomaly Detection](https://mlsanity.com/paper/2107.07820/) (2021)
- [Deep Contrastive One-Class Time Series Anomaly Detection](https://mlsanity.com/paper/2207.01472/) (2022)
- [Deep Anomaly Detection under Labeling Budget Constraints](https://mlsanity.com/paper/2302.07832/) (2023)
- [Unsupervised Anomaly Detection with Rejection](https://mlsanity.com/paper/2305.13189/) (2023)
- [TracInAD: Measuring Influence for Anomaly Detection](https://mlsanity.com/paper/2205.01362/) (2022)
- [Anomaly Detection with Variance Stabilized Density Estimation](https://mlsanity.com/paper/2306.00582/) (2023)
- [Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data](https://mlsanity.com/paper/2310.10461/) (2023)
- [Anomaly Detection and Generation with Diffusion Models: A Survey](https://mlsanity.com/paper/2506.09368/) (2025)
- [No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection](https://mlsanity.com/paper/2306.07284/) (2023)
- [DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection](https://mlsanity.com/paper/2307.06534/) (2023)
- [Self-Discriminative Modeling for Anomalous Graph Detection](https://mlsanity.com/paper/2310.06261/) (2023)
- [Towards One-for-All Anomaly Detection for Tabular Data](https://mlsanity.com/paper/2603.14407/) (2026)
- [Deep Anomaly Detection on Tennessee Eastman Process Data](https://mlsanity.com/paper/2303.05904/) (2023)
- [TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models](https://mlsanity.com/paper/2307.12336/) (2023)

## Abstract (arXiv)

Data transformations (e.g. rotations, reflections, and cropping) play an important role in self-supervised learning. Typically, images are transformed into different views, and neural networks trained on tasks involving these views produce useful feature representations for downstream tasks, including anomaly detection. However, for anomaly detection beyond image data, it is often unclear which transformations to use. Here we present a simple end-to-end procedure for anomaly detection with learnable transformations. The key idea is to embed the transformed data into a semantic space such that the transformed data still resemble their untransformed form, while different transformations are easily distinguishable. Extensive experiments on time series demonstrate that our proposed method outperforms existing approaches in the one-vs.-rest setting and is competitive in the more challenging n-vs.-rest anomaly detection task. On tabular datasets from the medical and cyber-security domains, our method learns domain-specific transformations and detects anomalies more accurately than previous work.