Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Qiyu, Luo, Huiyuan, Yao, Haiming, Luo, Wei, Qu, Zhen, Lv, Chengkan, Zhang, Zhengtao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913855169363968
author Chen, Qiyu
Luo, Huiyuan
Yao, Haiming
Luo, Wei
Qu, Zhen
Lv, Chengkan
Zhang, Zhengtao
author_facet Chen, Qiyu
Luo, Huiyuan
Yao, Haiming
Luo, Wei
Qu, Zhen
Lv, Chengkan
Zhang, Zhengtao
contents Anomaly detection plays a vital role in the inspection of industrial images. Most existing methods require separate models for each category, resulting in multiplied deployment costs. This highlights the challenge of developing a unified model for multi-class anomaly detection. However, the significant increase in inter-class interference leads to severe missed detections. Furthermore, the intra-class overlap between normal and abnormal samples, particularly in synthesis-based methods, cannot be ignored and may lead to over-detection. To tackle these issues, we propose a novel Center-aware Residual Anomaly Synthesis (CRAS) method for multi-class anomaly detection. CRAS leverages center-aware residual learning to couple samples from different categories into a unified center, mitigating the effects of inter-class interference. To further reduce intra-class overlap, CRAS introduces distance-guided anomaly synthesis that adaptively adjusts noise variance based on normal data distribution. Experimental results on diverse datasets and real-world industrial applications demonstrate the superior detection accuracy and competitive inference speed of CRAS. The source code and the newly constructed dataset are publicly available at https://github.com/cqylunlun/CRAS.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17551
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection
Chen, Qiyu
Luo, Huiyuan
Yao, Haiming
Luo, Wei
Qu, Zhen
Lv, Chengkan
Zhang, Zhengtao
Computer Vision and Pattern Recognition
Anomaly detection plays a vital role in the inspection of industrial images. Most existing methods require separate models for each category, resulting in multiplied deployment costs. This highlights the challenge of developing a unified model for multi-class anomaly detection. However, the significant increase in inter-class interference leads to severe missed detections. Furthermore, the intra-class overlap between normal and abnormal samples, particularly in synthesis-based methods, cannot be ignored and may lead to over-detection. To tackle these issues, we propose a novel Center-aware Residual Anomaly Synthesis (CRAS) method for multi-class anomaly detection. CRAS leverages center-aware residual learning to couple samples from different categories into a unified center, mitigating the effects of inter-class interference. To further reduce intra-class overlap, CRAS introduces distance-guided anomaly synthesis that adaptively adjusts noise variance based on normal data distribution. Experimental results on diverse datasets and real-world industrial applications demonstrate the superior detection accuracy and competitive inference speed of CRAS. The source code and the newly constructed dataset are publicly available at https://github.com/cqylunlun/CRAS.
title Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.17551