Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection
Variational autoencoders are widely used for unsupervised anomaly detection. Model selection however remains an open-question: to remain fully unsupervised, hyperparameters are often chosen to minimize the reconstruction error on normal samples. In this paper, we reveal a trade-off between reconstruction quality and anomaly detection among $β$-VAE models. Models with constrained latent space reach higher detection metrics but lower reconstruction quality. We also assess the performance variability across random seeds and show it is linked to the distance between normal and abnormal latent distributions. From this analysis, we justify and investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE. The latter especially shows an improvement in detection while maintaining high reconstruction quality.
Code (0)
등록된 구현이 없습니다.
Tasks
Unsupervised Anomaly DetectionSimilar Papers 제목 키워드 기반
FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection
Image reconstruction-based anomaly detection models are widely explored in industrial visual inspection. However, existing models usually suffer from the trade-off between normal reconstruction fidelity and abnormal reco…
Anomaly DetectionDefect DetectionImage ReconstructionImage RestorationUnsupervised Anomaly Detection Using Diffusion Trend Analysis
Conventional anomaly detection techniques based on reconstruction via denoising diffusion model are widely used due to their ability to identify anomaly locations and shapes with high performance. However, there is a lim…
Anomaly DetectionDenoisingUnsupervised Anomaly DetectionStatistical Non-linear Reconstruction Loss for Image Anomaly Detection
Reconstruction-based methods are a cornerstone of unsupervised image anomaly detection, but they remain vulnerable to \emph{outlier leakage}, where standard mean squared error (MSE) loss drives the model to faithfully re…
Anomaly DetectionOmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization
Unsupervised anomaly localization and detection is crucial for industrial manufacturing processes due to the lack of anomalous samples. Recent unsupervised advances on industrial anomaly detection achieve high perfor…
Anomaly DetectionAnomaly LocalizationMulti-class Anomaly DetectionODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects
This paper presents a novel framework for unsupervised anomaly detection on masked objects called ODDObjects, which stands for Out-of-Distribution Detection on Objects. ODDObjects is designed to detect anomalies of vario…
Anomaly DetectionImage ReconstructionObject RecognitionOut-of-Distribution Detection+1