Can I read Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation on EtoBox?

Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation by Hermary, Romain; Gaudillière, Vincent; Shabayek, Abd El Rahman; Aouada, Djamila is a scholarly article available to read on EtoBox.

What is Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation about?

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 co

Author

Hermary, Romain; Gaudillière, Vincent; Shabayek, Abd El Rahman; Aouada, Djamila

Published

2025

Language

EN