Unsupervised Anomaly Detection From Semantic Similarity Scores
Classifying samples as in-distribution or out-of-distribution (OOD) is a challenging problem of anomaly detection and a strong test of the generalisation power for models of the in-distribution. In this paper, we present a simple and generic framework, {\it SemSAD}, that makes use of a semantic similarity score to carry out anomaly detection. The idea is to first find for any test example the semantically closest examples in the training set, where the semantic relation between examples is quantified by the cosine similarity between feature vectors that leave semantics unchanged under transformations, such as geometric transformations (images), time shifts (audio signals), and synonymous word substitutions (text). A trained discriminator is then used to classify a test example as OOD if the semantic similarity to its nearest neighbours is significantly lower than the corresponding similarity for test examples from the in-distribution. We are able to outperform previous approaches for anomaly, novelty, or out-of-distribution detection in the visual domain by a large margin. In particular, we obtain AUROC values close to one for the challenging task of detecting examples from CIFAR-10 as out-of-distribution given CIFAR-100 as in-distribution, without making use of label information.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionOut-of-Distribution DetectionSemantic SimilaritySemantic Textual SimilarityUnsupervised Anomaly DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Copula Quadrant Similarity for Anomaly Scores
Practical anomaly detection requires applying numerous approaches due to the inherent difficulty of unsupervised learning. Direct comparison between complex or opaque anomaly detection algorithms is intractable; we inste…
Anomaly DetectionDINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features
Unsupervised anomaly detection (AD) in medical images aims to identify abnormal regions without relying on pixel-level annotations, which is crucial for scalable and label-efficient diagnostic systems. In this paper, we …
Unsupervised Anomaly DetectionExplainable Unsupervised Anomaly Detection with Random Forest
We describe the use of an unsupervised Random Forest for similarity learning and improved unsupervised anomaly detection. By training a Random Forest to discriminate between real data and synthetic data sampled from a un…
Anomaly DetectionFeature ImportanceUnsupervised Anomaly DetectionDQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches
Truly unsupervised approaches for time series anomaly detection are rare in the literature. Those that exist suffer from a poorly set threshold, which hampers detection performance, while others, despite claiming to be u…
Unsupervised Anomaly DetectionTime Series Anomaly DetectionActive LearningSLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA$^2$P, for unsupervised anomaly d…
Anomaly DetectionPseudo LabelSelf-Supervised Anomaly DetectionSelf-Supervised Learning+2