一种用于通用无监督异常检测的特征洗牌与恢复策略
A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection
AI总结：
本文提出FSR框架，通过多尺度特征洗牌与恢复缓解相同捷径问题，提升模型在不同场景下的通用性和效率。
摘要：
无监督异常检测在工业领域至关重要，基于重建的方法因其简单和有效性而被青睐。然而，重建方法常面临相同捷径问题，正常和异常区域均能被良好重建，无法识别异常。随着正常数据分布复杂性增加，该问题加剧。现有方法在特定场景表现优异，但转移至其他场景时性能急剧下降。本文旨在建立适用于不同设置的通用模型，称为通用异常检测。本文引入了一种新颖且高效的通用异常检测框架：特征洗牌与恢复（FSR），可缓解不同设置下的相同捷径问题。首先，FSR采用富含语义信息的多尺度特征作为重建目标，而非原始图像像素。随后，这些多尺度特征被划分为非重叠特征块，随机洗牌后通过恢复网络恢复原状。此简单范式促使模型更关注全局上下文信息。此外，我们引入了新的概念——洗牌率，以调节FSR任务的复杂性，从而缓解不同设置下的相同捷径问题。进一步，我们从网络结构和互信息两个角度提供了FSR框架有效性的理论解释。广泛实验结果验证了FSR框架在不同设置下的优越性和效率。代码可在https://github.com/luow23/FSR获取。
英文摘要：
Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal and anomalous regions can be well reconstructed and fail to identify outliers. The severity of this problem increases with the complexity of the normal data distribution. Consequently, existing methods may exhibit excellent detection performance in a specific scenario, but their performance sharply declines when transferred to another scenario. This paper focuses on establishing a universal model applicable to anomaly detection tasks across different settings, termed as universal anomaly detection. In this work, we introduce a novel, straightforward yet efficient framework for universal anomaly detection: \uline{F}eature \uline{S}huffling and \uline{R}estoration (FSR), which can alleviate the identical shortcut issue across different settings. First and foremost, FSR employs multi-scale features with rich semantic information as reconstruction targets, rather than raw image pixels. Subsequently, these multi-scale features are partitioned into non-overlapping feature blocks, which are randomly shuffled and then restored to their original state using a restoration network. This simple paradigm encourages the model to focus more on global contextual information. Additionally, we introduce a novel concept, the shuffling rate, to regulate the complexity of the FSR task, thereby alleviating the identical shortcut across different settings. Furthermore, we provide theoretical explanations for the effectiveness of FSR framework from two perspectives: network structure and mutual information. Extensive experimental results validate the superiority and efficiency of the FSR framework across different settings.Code is available at https://github.com/luow23/FSR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
