Zero-Shot Anomaly Detection

Overview

Zero-shot anomaly detection asks whether a model can flag, and often localize, patterns that depart from normality in a new domain without target-specific anomaly labels or training. Common approaches reuse frozen vision-language or vision foundation models with prompts, normal-reference comparisons, and patch or feature distances; others use geometric or frequency cues, lightweight adapters, or multimodal reasoning across images, video, 3D scans, time series, and graphs. Evaluation spans industrial defect benchmarks such as MVTec AD and VisA, surveillance video such as UCF-Crime, and medical, graph, and sensor data, using detection and localization metrics. A central tension is transferring to genuinely unseen anomaly types while balancing auxiliary data or prompt tuning against precise localization, calibrated recall, and practical inference cost.

Latest papers

92 papers5 papers in the last four weeks, level with the four weeks before. 0.0% of all new papers.

Sep 4, 2025

AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search

Text-based person anomaly search requires fine-grained alignment between language queries and subtle visual cues, a challenge amplified by the long-tailed nature of anomalous behaviors. While Large Multimodal Models (LMMs) offer powerful visual understanding, their generative pre-training is fundamentally misaligned with the discriminative needs of this retrieval task. Adapting them without costly fine-tuning remains a significant hurdle. We introduce AnomalyLMM, a training-free, coarse-to-fine framework that effectively repurposes generative LMMs for zero-shot anomaly retrieval. Our method first uses a general retrieval model to produce an initial ranking. To refine this list, we introduce a novel cloze-based re-ranking mechanism with three steps. The first step Cloze Generation converts the text query into a ``fill-in-the-blank'' prompt. Next, Cloze Completion compels the LMM to focus on specific visual regions and generate a description of the potential anomaly. The final step Comparison & Re-ranking calculates semantic alignment between the LMM's generated completion and the original query, which serves as a powerful re-ranking score. Experiments on the PAB and UCC datasets show that AnomalyLMM surpasses the competitive baseline by +1.93+1.93% and +1.79+1.79% Recall@1 accuracy on two datasets. Crucially, our method provides highly interpretable visual-textual alignments without any task-specific training, a vital feature for real-world deployment. The code will be made publicly available.
Feb 13, 2025

AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection

Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years. Existing generalist graph models have achieved remarkable success in different graph tasks but struggle to generalize to the GAD task. This limitation arises from their difficulty in learning generalized knowledge for capturing the inherently infrequent, irregular and heterogeneous abnormality patterns in graphs from different domains. To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets. One key insight is that graph-agnostic representations for normal and abnormal classes are required to support effective zero/few-shot GAD across different graphs. Motivated by this, AnomalyGFM is pre-trained to align data-independent, learnable normal and abnormal class prototypes with node representation residuals (i.e., representation deviation of a node from its neighbors). The residual features essentially project the node information into a unified feature space where we can effectively measure the abnormality of nodes from different graphs in a consistent way. This provides a driving force for the learning of graph-agnostic, discriminative prototypes for the normal and abnormal classes, which can be used to enable zero-shot GAD on new graphs, including very large-scale graphs. If there are few-shot labeled normal nodes available in the new graphs, AnomalyGFM can further support prompt tuning to leverage these nodes for better adaptation. Comprehensive experiments on 11 widely-used GAD datasets with real anomalies, demonstrate that AnomalyGFM significantly outperforms state-of-the-art competing methods under both zero- and few-shot GAD settings.