Training-free Anomaly Event Detection via LLM-guided Symbolic Pattern Discovery

2025-02-09

AI Summary

Unsupervised anomaly event detection suffers from poor interpretability and reliance on labeled data. Method: This paper proposes a training-free paradigm that integrates open-set object detection with symbolic regression, leveraging large language models (LLMs) to guide the construction of human-readable, symbolic logical rules for end-to-end entity-relation reasoning. Contribution/Results: The method requires zero training samples and achieves superior performance to supervised baselines using only 1% annotated data. It outputs interpretable logical expressions while maintaining high accuracy. Extensive evaluation across diverse anomaly scenarios demonstrates effectiveness. Additionally, we introduce a novel benchmark comprising over 110,000 private images and 5,000 annotated samples, advancing research in unsupervised, interpretable anomaly detection.

Technology Category

• Computer Vision: Visual Reasoning & Symbolic Representations
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Statistical Relational/Logic Learning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Anomaly event detection plays a crucial role in various real-world applications. However, current approaches predominantly rely on supervised learning, which faces significant challenges: the requirement for extensive labeled training data and lack of interpretability in decision-making processes. To address these limitations, we present a training-free framework that integrates open-set object detection with symbolic regression, powered by Large Language Models (LLMs) for efficient symbolic pattern discovery. The LLMs guide the symbolic reasoning process, establishing logical relationships between detected entities. Through extensive experiments across multiple domains, our framework demonstrates several key advantages: (1) achieving superior detection accuracy through direct reasoning without any training process; (2) providing highly interpretable logical expressions that are readily comprehensible to humans; and (3) requiring minimal annotation effort - approximately 1% of the data needed by traditional training-based methods.To facilitate comprehensive evaluation and future research, we introduce two datasets: a large-scale private dataset containing over 110,000 annotated images covering various anomaly scenarios including construction site safety violations, illegal fishing activities, and industrial hazards, along with a public benchmark dataset of 5,000 samples with detailed anomaly event annotations. Code is available at here.

Problem

• Training-free anomaly event detection
• LLM-guided symbolic pattern discovery
• Interpretable logical expressions for anomalies

Innovation

• Training-free anomaly detection
• LLM-guided symbolic discovery
• Minimal annotation effort required