2023/10/01 by Sarath Sivaprasad, Mario Fritz, Sivaprasad, Sarath +1
Computer Science · Engineering · Mathematics · Medicine · Psychology · #Anomaly (physics) #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #COVID-19 diagnosis using AI #Computer science #Data-Driven Disease Surveillance #Embedding #Engineering #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine learning #Matching (statistics) #Mathematics #Novelty #Novelty detection #Pattern recognition (psychology) #Psychology #Range (aeronautics) #Task (project management)
paper · pdf · doi:10.48550/arxiv.2310.00797
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/10/01 · openalex created_date 2023/10/04 · openalex updated_date 2026/07/28
Anomaly Detection (AD) is a critical task that involves identifying observations that do not conform to a learned model of normality. Prior work in deep AD is predominantly based on a familiarity hypothesis, where familiar features serve as the reference in a pre-trained embedding space. While this strategy has proven highly successful, it turns out that it causes consistent false negatives when anomalies consist of truly novel features that are not well captured by the pre-trained encoding. We propose a novel approach to AD using explainability to capture such novel features as unexplained observations in the input space. We achieve strong performance across a wide range of anomaly benchmarks by combining familiarity and novelty in a hybrid approach. Our approach establishes a new state-of-the-art across multiple benchmarks, handling diverse anomaly types while eliminating the need for expensive background models and dense matching. In particular, we show that by taking account of novel features, we reduce false negative anomalies by up to 40% on challenging benchmarks compared to the state-of-the-art. Our method gives visually inspectable explanations for pixel-level anomalies.