RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection
This work addresses the challenge of detecting defects in industrial settings without labeled data, offering a more efficient and practical solution compared to diffusion models, though it is incremental in improving autoencoder-based approaches.
The paper tackles the problem of incomplete anomaly suppression and loss of fine details in unsupervised industrial anomaly detection by proposing a recursive autoencoder framework that iteratively reconstructs images to progressively suppress anomalies and preserve textures. The method significantly outperforms existing non-diffusion methods and matches recent diffusion models with only 10% of their parameters and faster inference.
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.