Background-Aware Defect Generation for Robust Industrial Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Youngjae, Kim, Gwangyeol, Safarov, Sirojbek, Bang, Seongdeok, Park, Jaewoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915176243003392
author Cho, Youngjae
Kim, Gwangyeol
Safarov, Sirojbek
Bang, Seongdeok
Park, Jaewoo
author_facet Cho, Youngjae
Kim, Gwangyeol
Safarov, Sirojbek
Bang, Seongdeok
Park, Jaewoo
contents Detecting anomalies in industrial settings is challenging due to the scarcity of labeled anomalous data. Generative models can mitigate this issue by synthesizing realistic defect samples, but existing approaches often fail to model the crucial interplay between defects and their background. This oversight leads to unrealistic anomalies, especially in scenarios where contextual consistency is essential (i.e., logical anomaly). To address this, we propose a novel background-aware defect generation framework, where the background influences defect denoising without affecting the background itself by ensuring realistic synthesis while preserving structural integrity. Our method leverages a disentanglement loss to separate the background' s denoising process from the defect, enabling controlled defect synthesis through DDIM Inversion. We theoretically demonstrate that our approach maintains background fidelity while generating contextually accurate defects. Extensive experiments on MVTec AD and MVTec Loco benchmarks validate our mehtod's superiority over existing techniques in both defect generation quality and anomaly detection performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16767
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Background-Aware Defect Generation for Robust Industrial Anomaly Detection
Cho, Youngjae
Kim, Gwangyeol
Safarov, Sirojbek
Bang, Seongdeok
Park, Jaewoo
Computer Vision and Pattern Recognition
Artificial Intelligence
Detecting anomalies in industrial settings is challenging due to the scarcity of labeled anomalous data. Generative models can mitigate this issue by synthesizing realistic defect samples, but existing approaches often fail to model the crucial interplay between defects and their background. This oversight leads to unrealistic anomalies, especially in scenarios where contextual consistency is essential (i.e., logical anomaly). To address this, we propose a novel background-aware defect generation framework, where the background influences defect denoising without affecting the background itself by ensuring realistic synthesis while preserving structural integrity. Our method leverages a disentanglement loss to separate the background' s denoising process from the defect, enabling controlled defect synthesis through DDIM Inversion. We theoretically demonstrate that our approach maintains background fidelity while generating contextually accurate defects. Extensive experiments on MVTec AD and MVTec Loco benchmarks validate our mehtod's superiority over existing techniques in both defect generation quality and anomaly detection performance.
title Background-Aware Defect Generation for Robust Industrial Anomaly Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2411.16767