电子科技大学学报2024，Vol.53Issue(3)：424-430,7.DOI:10.12178/1001-0548.2024032
基于近似存在性查询的高效图像异常检测方法
An Efficient Image Anomaly Detection Approach Based on Approximate Membership Query
摘要
Abstract
An accurate and stable approach to image anomaly detection is to query the K-nearest neighbours of the image features from normal examples and estimate the anomaly score,relying on Approximate Nearest Neighbour Search(ANNS)indices.ANNS query operation has high computational cost on large datasets,unpractical for low-latency and high-throughput scenarios.Based on locality sensitive Hashing and Bloom filters,an Approximated Membership Query(AMQ)based approach is proposed to predict anomalies by approximate membership of features.AMQ can address the performance bottleneck of search-based methods,given its lower complexity and better compatibility with single-instruction multiple-data parallelism than ANNS.Experimental results on MVTec-AD show that the accuracy of AMQ-based method is just decreased about 1%in comparison with ANNS-based methods,while the inference latency,the throughput and the memory footprint are significantly improved,close to the efficiency of end-to-end deep learning anomaly detection models.关键词
异常检测/无监督学习/近似存在性查询/布隆过滤器/局部敏感哈希Key words
anomaly detection/unsupervised learning/approximate membership query/Bloom filter/locality sensitive hashing分类
信息技术与安全科学引用本文复制引用
伍凌川,史慧芳,邱枫,石义官..基于近似存在性查询的高效图像异常检测方法[J].电子科技大学学报,2024,53(3):424-430,7.基金项目
国防基础科研项目(JCKY2022209A002) （JCKY2022209A002）
国家自然科学基金重点项目(T2293771) （T2293771）
