Wavelet-Enhanced PaDiM for Industrial Anomaly Detection
Open Access
- 3 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 37702-37718
Abstract
Anomaly detection (AD) and localization in industrial images are essential for automated quality inspection. PaDiM models normality using multivariate Gaussian distributions over deep features, but typically relies on random channel selection for dimensionality reduction. This limits interpretability and potentially discards structured information. We propose Wavelet-Enhanced PaDiM (WE-PaDiM), which replaces random selection with a structured frequency-domain feature selection strategy using the 2D Discrete Wavelet Transform (DWT) as its core component to decompose CNN features into interpretable frequency subbands before modeling. Specifically, DWT is applied independently to multi-layer CNN feature maps, selected subband coefficients are spatially aligned, and the resulting representations are concatenated prior to PaDiM modeling. We evaluate WE-PaDiM on MVTec AD and VisA datasets across ResNet-18 and EfficientNet-b0–b6 backbones. Under per-category configuration selection, WE-PaDiM achieves 99.32% Image-AUC on MVTec AD (image-optimized) and 96.65% Pixel-AUC (pixel-optimized), and achieves 93.59% Image-AUC on VisA (image-optimized) and 96.43% Pixel-AUC (pixel-optimized). These image- and pixel-optimized results correspond to distinct operating points (potentially selecting different configurations), rather than a single jointly-achieved setting. Notably, the dominant fixed pixel-level operating point is Haar/L1/LL (low-frequency) on both datasets, while per-category pixel-optimal selections are largely LL-dominant with a small number of VisA exceptions. WE-PaDiM offers deterministic and interpretable feature selection with competitive computational characteristics.Keywords
All Related Versions
Funding Information
- Science and Technology Center in Ukraine (20014131)
- “25nm X ray Inspection System for Semiconductor Backend Process”
- Ministry of Trade, Industry and Energy
- National Science Foundation (2430236)
- Regional Innovation System & Education (RISE) through the Seoul RISE Center
- Ministry of Education (MOE) and the Seoul Metropolitan Government (2026-RISE-01-019-04)
This publication has 26 references indexed in Scilit:
- Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detectionCAAI Transactions on Intelligence Technology, 2023
- SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation2022
- PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization2021
- MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection2019
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery2017
- Deep Residual Learning for Image Recognition2016
- Group Invariant ScatteringCommunications on Pure and Applied Mathematics, 2012
- ImageNet: A large-scale hierarchical image database2009
- De-noising by soft-thresholdingIEEE Transactions on Information Theory, 1995
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989