Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wu, Rongcheng, Zhu, Hao, Zhang, Shiying, Wang, Mingzhe, Li, Zhidong, Li, Hui, Zhou, Jianlong, Cui, Jiangtao, Chen, Fang, Sun, Pingyang, Liao, Qiyu, Lin, Ye
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.11284
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911315685015552
author Wu, Rongcheng
Zhu, Hao
Zhang, Shiying
Wang, Mingzhe
Li, Zhidong
Li, Hui
Zhou, Jianlong
Cui, Jiangtao
Chen, Fang
Sun, Pingyang
Liao, Qiyu
Lin, Ye
author_facet Wu, Rongcheng
Zhu, Hao
Zhang, Shiying
Wang, Mingzhe
Li, Zhidong
Li, Hui
Zhou, Jianlong
Cui, Jiangtao
Chen, Fang
Sun, Pingyang
Liao, Qiyu
Lin, Ye
contents Unsupervised industrial anomaly detection requires accurately identifying defects without labeled data. Traditional autoencoder-based methods often struggle with incomplete anomaly suppression and loss of fine details, as their single-pass decoding fails to effectively handle anomalies with varying severity and scale. We propose a recursive architecture for autoencoder (RcAE), which performs reconstruction iteratively to progressively suppress anomalies while refining normal structures. Unlike traditional single-pass models, this recursive design naturally produces a sequence of reconstructions, progressively exposing suppressed abnormal patterns. To leverage this reconstruction dynamics, we introduce a Cross Recursion Detection (CRD) module that tracks inconsistencies across recursion steps, enhancing detection of both subtle and large-scale anomalies. Additionally, we incorporate a Detail Preservation Network (DPN) to recover high-frequency textures typically lost during reconstruction. Extensive experiments demonstrate that our method significantly outperforms existing non-diffusion methods, and achieves performance on par with recent diffusion models with only 10% of their parameters and offering substantially faster inference. These results highlight the practicality and efficiency of our approach for real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection
Wu, Rongcheng
Zhu, Hao
Zhang, Shiying
Wang, Mingzhe
Li, Zhidong
Li, Hui
Zhou, Jianlong
Cui, Jiangtao
Chen, Fang
Sun, Pingyang
Liao, Qiyu
Lin, Ye
Computer Vision and Pattern Recognition
Unsupervised industrial anomaly detection requires accurately identifying defects without labeled data. Traditional autoencoder-based methods often struggle with incomplete anomaly suppression and loss of fine details, as their single-pass decoding fails to effectively handle anomalies with varying severity and scale. We propose a recursive architecture for autoencoder (RcAE), which performs reconstruction iteratively to progressively suppress anomalies while refining normal structures. Unlike traditional single-pass models, this recursive design naturally produces a sequence of reconstructions, progressively exposing suppressed abnormal patterns. To leverage this reconstruction dynamics, we introduce a Cross Recursion Detection (CRD) module that tracks inconsistencies across recursion steps, enhancing detection of both subtle and large-scale anomalies. Additionally, we incorporate a Detail Preservation Network (DPN) to recover high-frequency textures typically lost during reconstruction. Extensive experiments demonstrate that our method significantly outperforms existing non-diffusion methods, and achieves performance on par with recent diffusion models with only 10% of their parameters and offering substantially faster inference. These results highlight the practicality and efficiency of our approach for real-world applications.
title RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.11284