paper-with-me

홈 › Papers

Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization

2023-07-06 · Shiqi Deng, Zhiyu Sun, Ruiyan Zhuang, Jun Gong

Anomaly detection has a wide range of applications and is especially important in industrial quality inspection. Currently, many top-performing anomaly-detection models rely on feature-embedding methods. However, these methods do not perform well on datasets with large variations in object locations. Reconstruction-based methods use reconstruction errors to detect anomalies without considering positional differences between samples. In this study, a reconstruction-based method using the noise-to-norm paradigm is proposed, which avoids the invariant reconstruction of anomalous regions. Our reconstruction network is based on M-net and incorporates multiscale fusion and residual attention modules to enable end-to-end anomaly detection and localization. Experiments demonstrate that the method is effective in reconstructing anomalous regions into normal patterns and achieving accurate anomaly detection and localization. On the MPDD and VisA datasets, our proposed method achieved more competitive results than the latest methods, and it set a new state-of-the-art standard on the MPDD dataset.

📄 PDF Abstract BibTeX arXiv:2307.02836

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Similar Papers 제목 키워드 기반

Removing Anomalies as Noises for Industrial Defect Localization

2023-01-01 · ICCV 2023 1 · Fanbin Lu, Xufeng Yao, Chi-Wing Fu, Jiaya Jia

Unsupervised anomaly detection aims to train models with only anomaly-free images to detect and localize unseen anomalies. Previous reconstruction-based methods have been limited by inaccurate reconstruction results.…

Anomaly DetectionAnomaly LocalizationDenoisingImage Reconstruction+1

Unsupervised Anomaly Detection Using Diffusion Trend Analysis

2024-07-12 · Eunwoo Kim, Un Yang, Cheol Lae Roh, Stefano Ermon

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 Detection

Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection

2024-06-17 · Haiming Yao, Yunkang Cao, Wei Luo, Weihang Zhang 외

Image anomaly detection plays a pivotal role in industrial inspection. Traditional approaches often demand distinct models for specific categories, resulting in substantial deployment costs. This raises concerns about mu…

Anomaly DetectionMulti-class Anomaly Detection

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

2023-03-15 · HUI ZHANG, Zheng Wang, Dan Zeng, Zuxuan Wu 외

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconst…

Anomaly DetectionDenoisingUnsupervised Anomaly Detection

Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection

2025-12-12 · Qishan Wang, Haofeng Wang, Shuyong Gao, Jia Guo 외 arxiv

Industrial anomaly detection is a challenging open-set task that aims to identify unknown anomalous patterns deviating from normal data distribution. To avoid the significant memory consumption and limited generalizabili…

Multi-class Anomaly Detection