Saved in:
Bibliographic Details
Main Authors: Huang, Huichuan, Zhong, Zhiqing, Wei, Guangyu, Wan, Yonghao, Sun, Wenlong, Feng, Aimin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00609
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910900799143936
author Huang, Huichuan
Zhong, Zhiqing
Wei, Guangyu
Wan, Yonghao
Sun, Wenlong
Feng, Aimin
author_facet Huang, Huichuan
Zhong, Zhiqing
Wei, Guangyu
Wan, Yonghao
Sun, Wenlong
Feng, Aimin
contents In image anomaly detection, significant advancements have been made using un- and self-supervised methods with datasets containing only normal samples. However, these approaches often struggle with fine-grained anomalies. This paper introduces \textbf{GRAD}: Bi-\textbf{G}rid \textbf{R}econstruction for Image \textbf{A}nomaly \textbf{D}etection, which employs two continuous grids to enhance anomaly detection from both normal and abnormal perspectives. In this work: 1) Grids as feature repositories that improve generalization and mitigate the Identical Shortcut (IS) issue; 2) An abnormal feature grid that refines normal feature boundaries, boosting detection of fine-grained defects; 3) The Feature Block Paste (FBP) module, which synthesizes various anomalies at the feature level for quick abnormal grid deployment. GRAD's robust representation capabilities also allow it to handle multiple classes with a single model. Evaluations on datasets like MVTecAD, VisA, and GoodsAD show significant performance improvements in fine-grained anomaly detection. GRAD excels in overall accuracy and in discerning subtle differences, demonstrating its superiority over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00609
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bi-Grid Reconstruction for Image Anomaly Detection
Huang, Huichuan
Zhong, Zhiqing
Wei, Guangyu
Wan, Yonghao
Sun, Wenlong
Feng, Aimin
Computer Vision and Pattern Recognition
Machine Learning
In image anomaly detection, significant advancements have been made using un- and self-supervised methods with datasets containing only normal samples. However, these approaches often struggle with fine-grained anomalies. This paper introduces \textbf{GRAD}: Bi-\textbf{G}rid \textbf{R}econstruction for Image \textbf{A}nomaly \textbf{D}etection, which employs two continuous grids to enhance anomaly detection from both normal and abnormal perspectives. In this work: 1) Grids as feature repositories that improve generalization and mitigate the Identical Shortcut (IS) issue; 2) An abnormal feature grid that refines normal feature boundaries, boosting detection of fine-grained defects; 3) The Feature Block Paste (FBP) module, which synthesizes various anomalies at the feature level for quick abnormal grid deployment. GRAD's robust representation capabilities also allow it to handle multiple classes with a single model. Evaluations on datasets like MVTecAD, VisA, and GoodsAD show significant performance improvements in fine-grained anomaly detection. GRAD excels in overall accuracy and in discerning subtle differences, demonstrating its superiority over existing methods.
title Bi-Grid Reconstruction for Image Anomaly Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.00609