ONER：用于增量异常检测的在线经验回放
ONER: Online Experience Replay for Incremental Anomaly Detection
AI总结：
ONER提出在线经验回放框架，通过分解提示和语义原型解决增量异常检测中的灾难性遗忘，在MVTec AD上以0.019M参数实现像素AUROC和AUPR分别提升4.4%和28.3%。
摘要：
增量异常检测旨在顺序识别工业生产线中的缺陷，但遭受灾难性遗忘，这主要归因于参数更新期间的知识覆盖和任务间的特征冲突。在本工作中，我们提出ONER（在线经验回放），一个端到端框架，通过协同整合两种类型的经验来解决这些问题：（1）分解提示，从可重用模块动态生成图像条件提示以保留先前知识，从而防止知识覆盖；（2）语义原型，在像素和图像级别的潜在特征空间中强制可分离性，以缓解跨任务特征冲突。大量实验证明了ONER的优越性，在MVTec AD数据集上实现了最先进的性能，像素AUROC提升+4.4%，像素AUPR提升+28.3%，优于先前方法。值得注意的是，ONER仅使用0.019M参数和每个任务5个训练周期就实现了这一性能，证实了其在实际工业部署中的效率和稳定性。
英文摘要：
Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks. In this work, We propose ONER (ONline Experience Replay), an end-to-end framework that addresses these issues by synergistically integrating two types of experience: (1) decomposed prompts, which dynamically generate image-conditioned prompts from reusable modules to retain prior knowledge thus prevent knowledge overwriting, and (2) semantic prototypes, which enforce separability in latent feature spaces at pixel and image levels to mitigate cross-task feature conflicts. Extensive experiments demonstrate the superiority of ONER, achieving state-of-the-art performance with +4.4% Pixel AUROC and +28.3% Pixel AUPR improvements on the MVTec AD dataset over prior methods. Remarkably, ONER achieves this with only 0.019M parameters and 5 training epochs per task, confirming its efficiency and stability for real-world industrial deployment.
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。
