paper-with-me

홈 › Papers

Unsupervised Anomaly Detection From Semantic Similarity Scores

2020-12-01 · Nima Rafiee, Rahil Gholamipoor, Markus Kollmann

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.

📄 PDF Abstract BibTeX arXiv:2012.00461

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly DetectionOut-of-Distribution DetectionSemantic SimilaritySemantic Textual SimilarityUnsupervised Anomaly Detection

Methods 이 논문이 사용한 방법론

InfoNCE 설명 없음
Contrastive Predictive Coding Contrastive Predictive Coding (CPC) learns self-supervised representations by predicting the future in latent space by using powerful autoregressive models. The model uses a…

Similar Papers 제목 키워드 기반

Copula Quadrant Similarity for Anomaly Scores

2021-01-07 · Matthew Davidow, David Matteson

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 Detection

DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features

2026-01-31 · Jiayu Huo, Jingyuan Hong, Liyun Chen arxiv

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 Detection

Explainable Unsupervised Anomaly Detection with Random Forest

2025-04-22 · Joshua S. Harvey, Joshua Rosaler, Mingshu Li, Dhruv Desai 외

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 Detection

DQS: A Low-Budget Query Strategy for Enhancing Unsupervised Data-driven Anomaly Detection Approaches

2025-09-06 · Lucas Correia, Jan-Christoph Goos, Thomas Bäck, Anna V. Kononova arxiv

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 Learning

SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation

2021-11-25 · Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu 외

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