用统一内存池实现持续异常检测，避免遗忘且精度领先。
CADIC: Continual Anomaly Detection Based on Incremental Coreset
- 所有任务共享一个固定大小的紧凑记忆池，增量更新嵌入向量。
- 在MVTec AD和Visa数据集上图像级AUROC分别达0.972和0.891。
- 适用于工业缺陷检测等需持续学习的真实场景。
持续异常检测（CAD）的目标是在动态数据分布下学习新任务的正常模式，同时缓解灾难性遗忘。现有基于嵌入的方法通过不断向记忆库添加新嵌入来适应序列任务，但需为每项任务构建独立的子记忆库，限制了灵活性与可扩展性。为此，我们提出一种新框架，所有任务共享统一记忆库。训练时，方法在固定大小的共核（coreset）内增量更新嵌入，实现无需任务专属记忆碎片的连续知识获取。推理阶段通过最近邻匹配计算异常分数，达到当前最优检测精度。在MVTec AD和Visa数据集上的全面实验表明，该方法优于现有基线，图像级平均AUROC分别为0.972（MVTec AD）和0.891（Visa）。尤其在真实世界电子纸数据集上，异常样本检测准确率达100%，验证其在实际应用中的鲁棒性。代码将开源于GitHub。
原文摘要 · Abstract (English)
The primary objective of Continual Anomaly Detection (CAD) is to learn the normal patterns of new tasks under dynamic data distribution assumptions while mitigating catastrophic forgetting. Existing embedding-based CAD approaches continuously update a memory bank with new embeddings to adapt to sequential tasks. However, these methods require constructing class-specific sub-memory banks for each task, which restricts their flexibility and scalability. To address this limitation, we propose a novel CAD framework where all tasks share a unified memory bank. During training, the method incrementally updates embeddings within a fixed-size coreset, enabling continuous knowledge acquisition from sequential tasks without task-specific memory fragmentation. In the inference phase, anomaly scores are computed via a nearest-neighbor matching mechanism, achieving state-of-the-art detection accuracy. We validate the method through comprehensive experiments on MVTec AD and Visa datasets. Results show that our approach outperforms existing baselines, achieving average image-level AUROC scores of 0.972 (MVTec AD) and 0.891 (Visa). Notably, on a real-world electronic paper dataset, it demonstrates 100% accuracy in anomaly sample detection, confirming its robustness in practical scenarios. The implementation will be open-sourced on GitHub.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。