Few-Shot Anomaly Detection

Follow this topic Ask about this topic

Few-shot anomaly detection studies how to recognize unusual examples when only a few references—often normal samples, and sometimes labeled anomalies—are available. Common approaches compare pretrained visual or language features with support examples, build prototype or memory banks, model normality through reconstruction or subspaces, and adapt detectors with lightweight prompts or calibration. The methods are used in settings such as industrial defect inspection, medical imaging, graphs, audio, and time series, where collecting labels can be costly. A central challenge is making results transfer reliably across categories and distribution shifts while controlling reference contamination and setting trustworthy detection thresholds.

Latest papers

40 papers6 papers in the last four weeks, up 20% on the four weeks before. 0.0% of all new papers.

LLM-Enhanced Log Anomaly Detection: A Comprehensive Benchmark of Large Language Models for Automated System Diagnostics
Apr 14, 2026Disha PatelAnomaly Detection Online Anomaly Detection
Department of Computer Science, California State University, Fullerton
InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation
Apr 6, 2026Jiawen Zhu, Mengjia Niu, Guansong PangAnomaly Detection Few-Shot Anomaly Detection
School of Computing and Information Systems, Singapore Management University, Singapore. · Dyson School of Design Engineering, Imperial College London, United Kingdom.
One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
Mar 18, 2026Haoxiang Rao, Zhao Wang, Chenyang Si +4Synthetic Anomaly Generation Industrial Anomaly Detection
Nanjing University · China Mobile Zijin Innovation Institute · Shandong University of Science and Technology
GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
Mar 16, 2026Aggelos Psiris, Yannis Panagakis, Maria Vakalopoulou +1Few-Shot Anomaly Detection Industrial Anomaly Detection
Harokopio University of Athens, Athens, Greece · National and Kapodistrian University of Athens, Athens, Greece · Archimedes, Athena Research Center, Athens, Greece +1
Dual Distillation for Few-Shot Anomaly Detection
Mar 2, 2026Le Dong, Qinzhong Tan, Chunlei Li +5Few-Shot Anomaly Detection Anomaly Detection
Xidian University, China · MedAI Technology (Wuxi) Co. Ltd., China · Technical University of Munich, Germany
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
Feb 26, 2026Camile Lendering, Erkut Akdag, Egor BondarevFew-Shot Anomaly Detection Anomaly Detection
AIMS Group, Department of Electrical Engineering, Eindhoven University of Technology
RAID: Retrieval-Augmented Anomaly Detection
Feb 23, 2026Mingxiu Cai, Zhe Zhang, Gaochang Wu +2Unsupervised Anomaly Detection Anomaly Detection
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University · University of Surrey
From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection
Feb 21, 2026Yixin Liu, Shiyuan Li, Yu Zheng +4Anomaly Detection Zero-Shot Anomaly Detection
School of Information and Communication Technology, Griffith University, Australia. · School of Computer, Electronics and Information, Guangxi University, Nanning, China. · Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong. +1
Adversarially Robust Few-Shot Anomaly Detection with Vision Foundation Models
Oct 15, 2025Akib Mohammed Khan, Bartosz KrawczykFew-Shot Anomaly Detection Anomaly Detection
Rochester Institute of Technology Rochester, USA
AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
Feb 13, 2025Hezhe Qiao, Chaoxi Niu, Ling Chen +1Graph-Based Anomaly Detection Anomaly Detection
School of Computing and Information Systems Singapore Management University Singapore · Australian Artificial Intelligence Institute University of Technology Sydney Sydney, Australia

Apr 14, 2026J/K move · Enter open · S save

LLM-Enhanced Log Anomaly Detection: A Comprehensive Benchmark of Large Language Models for Automated System Diagnostics

Disha Patel

Department of Computer Science, California State University, Fullerton

Anomaly Detection Online Anomaly Detection Few-Shot Anomaly Detection LLM Evaluation Zero-Shot Anomaly Detection

Open paper AskPDF arXiv

System log anomaly detection is critical for maintaining the reliability of large-scale software systems, yet traditional methods struggle with the heterogeneous and evolving nature of modern log data. Recent advances in Large Language Models (LLMs) offer promising new approaches to log understanding, but a systematic comparison of LLM-based methods against established techniques remains lacking. In this paper, we present a comprehensive benchmark study evaluating both LLM-based and traditional approaches for log anomaly detection across four widely-used public datasets: HDFS, BGL, Thunderbird, and Spirit. We evaluate three categories of methods: (1) classical log parsers (Drain, Spell, AEL) combined with machine learning classifiers, (2) fine-tuned transformer models (BERT, RoBERTa), and (3) prompt-based LLM approaches (GPT-3.5, GPT-4, LLaMA-3) in zero-shot and few-shot settings. Our experiments reveal that while fine-tuned transformers achieve the highest F1-scores (0.96-0.99), prompt-based LLMs demonstrate remarkablezero-shot capabilities (F1: 0.82-0.91) without requiring any labeled training data -- a significant advantage for real-world deployment where labeled anomalies are scarce. We further analyze the cost-accuracy trade-offs, latency characteristics, and failure modes of each approach. Our findings provide actionable guidelines for practitioners choosing log anomaly detection methods based on their specific constraints regarding accuracy, latency, cost, and label availability. All code and experimental configurations are publicly available to facilitate reproducibility.