Statistical 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 reconstruct anomalous patterns. We propose a Non-linear Reconstruction Loss that applies a sigmoid-based squashing function to suppress high-magnitude features, preventing outliers from dominating optimization while preserving sensitivity to normal patterns. In addition, we introduce a statistical calibration scheme that selects the scaling factor $k$ from the confidence interval (CI) of the normal feature distribution, enabling data-driven control of the suppression strength. Our approach achieves competitive or superior anomaly detection performance compared to state-of-the-art methods, reaching 99.0\% Image-AUROC and 97.3\% Pixel-AUROC on MVTec-AD, and 95.3\% Image-AUROC and 99.0\% Pixel-AUROC on VisA. These results indicate that non-linear gradient suppression is an effective mechanism for mitigating outlier leakage and improving anomaly localization in unified industrial inspection settings. The implementation is available at https://github.com/mintii13/Statistical-Non-linear-Reconstruction-Loss.git.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionResults from the Paper
| Rank | Task | Dataset | Model | Metrics |
|---|---|---|---|---|
| #4 | Anomaly Detection | VisA | Non-linear | Detection AUROC: 99.0 |
Similar Papers 제목 키워드 기반
DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images. Most image reconstruction based AD methods rely on the discriminative capability of reco…
Adversarial AttackAdversarial Attack DetectionAnomaly DetectionBenchmarking+1Anomaly Detection By Autoencoder Based On Weighted Frequency Domain Loss
In image anomaly detection, Autoencoders are the popular methods that reconstruct the input image that might contain anomalies and output a clean image with no abnormalities. These Autoencoder-based methods usually calcu…
Anomaly DetectionCOGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
Reconstruction-based methods are a dominant paradigm in time series anomaly detection (TSAD), however, their near-universal reliance on Mean Squared Error (MSE) loss results in statistically flawed reconstruction residua…
Time Series Anomaly DetectionFRE: A Fast Method For Anomaly Detection And Segmentation
This paper presents a fast and principled approach for solving the visual anomaly detection and segmentation problem. In this setup, we have access to only anomaly-free training data and want to detect and identify anoma…
Anomaly DetectionCPUDimensionality ReductionAutoencoders for Anomaly Detection are Unreliable
Autoencoders are frequently used for anomaly detection, both in the unsupervised and semi-supervised settings. They rely on the assumption that when trained using the reconstruction loss, they will be able to reconstruct…
Anomaly Detection