Target Before Shooting: Accurate Anomaly Detection And Localization Under One Millisecond Via Cascade Patch Retrieval

Abstract

In this work, by re-examining the "matching" nature of Anomaly Detection (AD), we propose a new AD framework that simultaneously enjoys new records of AD accuracy and dramatically high running speed. In this framework, the anomaly detection problem is solved via a cascade patch retrieval procedure that retrieves the nearest neighbors for each test image patch in a coarse-to-fine fashion. Given a test sample, the top-K most similar training images are first selected based on a robust histogram matching process. Secondly, the nearest neighbor of each test patch is retrieved over the similar geometrical locations on those "global nearest neighbors", by using a carefully trained local metric. Finally, the anomaly score of each test image patch is calculated based on the distance to its "local nearest neighbor" and the "non-background" probability. The proposed method is termed "Cascade Patch Retrieval" (CPR) in this work. Different from the conventional patch-matching-based AD algorithms,

Stats

• citations24
• S2 citations—
• github stars116
• HF likes0
• heat score14.62
• arxiv keyli2023target

Related papers

• MRAD: Zero-shot Anomaly Detection With Memory-driven Retrieval (2026)4.01
• Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching (2025)0.00
• Quantifying Statistical Significance Of Deep Nearest Neighbor Anomaly Detection Via Selective Inference (2025)0.00
• Context Recovery And Knowledge Retrieval: A Novel Two-stream Framework For Video Anomaly Detection (2022)11.39
• Learnable Locality-sensitive Hashing For Video Anomaly Detection (2021)12.02
• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47
• Superncn: Neighbourhood Consensus Network For Robust Outdoor Scenes Matching (2019)2.26
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00