Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| 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 |