# Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation

arXiv: https://arxiv.org/abs/2503.05520 · HTML: https://mlsanity.com/paper/2503.05520/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 63 references that are in the map.
- First posted on arXiv 7 Mar 2025.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates](https://mlsanity.com/paper/1708.07120/) (2017)
- [OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations](https://mlsanity.com/paper/1903.08550/) (2019)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [Deep Learning for Medical Anomaly Detection -- A Survey](https://mlsanity.com/paper/2012.02364/) (2020)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection](https://mlsanity.com/paper/2201.02331/) (2022)
- [Perturbation Learning Based Anomaly Detection](https://mlsanity.com/paper/2206.02704/) (2022)
- [Deep Orthogonal Hypersphere Compression for Anomaly Detection](https://mlsanity.com/paper/2302.06430/) (2023)
- [Novelty Detection via Contrastive Learning with Negative Data Augmentation](https://mlsanity.com/paper/2106.09958/) (2021)

## Built on by (most cited first, 2 of 2)

- [ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection](https://mlsanity.com/paper/2604.13924/) (2026)
- [An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detection](https://mlsanity.com/paper/2607.22286/) (2026)

## Abstract (arXiv)

One-class anomaly detection aims to detect objects that do not belong to a predefined normal class. In practice training data lack those anomalous samples; hence state-of-the-art methods are trained to discriminate between normal and synthetically-generated pseudo-anomalous data. Most methods use data augmentation techniques on normal images to simulate anomalies. However the best-performing ones implicitly leverage a geometric bias present in the benchmarking datasets. This limits their usability in more general conditions. Others are relying on basic noising schemes that may be suboptimal in capturing the underlying structure of normal data. In addition most still favour the image domain to generate pseudo-anomalies training models end-to-end from only the normal class and overlooking richer representations of the information. To overcome these limitations we consider frozen yet rich feature spaces given by pretrained models and create pseudo-anomalous features with a novel adaptive linear feature perturbation technique. It adapts the noise distribution to each sample applies decaying linear perturbations to feature vectors and further guides the classification process using a contrastive learning objective. Experimental evaluation conducted on both standard and geometric bias-free datasets demonstrates the superiority of our approach with respect to comparable baselines. The codebase is accessible via our public repository.