隔离以利用：面向完全无监督异常检测的跨分区蒸馏
Isolating to Harness: Cross-Division Distillation for Fully Unsupervised Anomaly Detection
AI总结：
针对训练数据含未标记异常的完全无监督异常检测场景，提出跨分区蒸馏框架，通过隔离异常影响并跨分区协作生成伪监督，在噪声AD数据集上性能优于基线。
摘要：
完全无监督异常检测（FUAD）针对训练数据受未标记异常污染的实际场景，该设置对传统无监督异常检测（UAD）方法构成关键挑战，因为传统方法易将训练异常误判为正常模式，导致假阴性。尽管从训练集中过滤异常是常用对策，但这不可避免会丢弃有价值数据，降低模型对正常性的表征能力。为克服这一困境，我们提出“隔离以利用”策略，该策略在专用分区内隔离异常的影响，然后利用跨分区协作生成鲁棒的伪监督。我们基于广泛研究的反向蒸馏范式，通过新颖的跨分区蒸馏（Cross-Division Distillation, CDD）框架实现该思路。CDD首先将数据划分为异常比例降低的分区，以训练分区专属学生模型；随后聚合各分区专属学生为其他数据分区样本生成的伪正常特征，指导全局学生模型学习鲁棒的无异常表征。在多个异常检测（AD）数据集的噪声版本上的实验结果表明，我们的方法相比基线实现了显著的性能提升。代码可在指定URL获取。
英文摘要：
Fully Unsupervised Anomaly Detection (FUAD) addresses the practical scenario where training data is contaminated with unlabeled anomalies. This setting critically challenges conventional Unsupervised Anomaly Detection (UAD) methods, as they tend to misinterpret training anomalies as normal patterns, leading to false negatives. Although filtering anomalies from the training set is a common countermeasure, it inevitably discards valuable data and degrades the model's representation of normality. To overcome this dilemma, we propose an "isolating to harness" strategy, which isolates the influence of anomalies within specialized divisions and then leverages cross-division collaboration to generate robust pseudo supervision. We materialize this idea via a novel Cross-Division Distillation framework based on the widely studied Reverse Distillation paradigm. CDD first partitions the data into divisions with reduced anomaly ratios to train division-specific students. It then aggregates pseudo-normal features generated by each division-specific student for samples from other data divisions to guide a global student towards a robust anomaly-free representation. Experimental results on noisy versions of multiple AD datasets demonstrate that our method achieves significant performance improvements over the baseline. Code is available at https://github.com/hito2448/CDD.
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。
