VID-AD: A Dataset for Image-Level Logical Anomaly Detection under Vision-Induced Distraction

2026-03-14

AI Summary

This study addresses the challenge of detecting logical-rule violations in industrial visual inspection under complex real-world conditions such as cluttered backgrounds, illumination variations, and motion blur—factors that hinder existing methods. To this end, the authors introduce VID-AD, a novel dataset comprising 10 manufacturing scenarios under five imaging conditions, yielding 50 one-class tasks with 10,395 images. Each scenario explicitly defines two logical constraints and provides the first benchmark where logical states remain fixed while visual perturbations are systematically controlled. The work further proposes a language-driven anomaly detection framework that leverages only normal samples to generate textual descriptions and incorporates contradictory negative samples via contrastive learning to enhance sensitivity to logical attributes. Experiments demonstrate that the proposed method significantly outperforms current baselines across multiple settings, effectively identifying anomalies at the logical level rather than relying on low-level visual discrepancies.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance

Abstract

Logical anomaly detection in industrial inspection remains challenging due to variations in visual appearance (e.g., background clutter, illumination shift, and blur), which often distract vision-centric detectors from identifying rule-level violations. However, existing benchmarks rarely provide controlled settings where logical states are fixed while such nuisance factors vary. To address this gap, we introduce VID-AD, a dataset for logical anomaly detection under vision-induced distraction. It comprises 10 manufacturing scenarios and five capture conditions, totaling 50 one-class tasks and 10,395 images. Each scenario is defined by two logical constraints selected from quantity, length, type, placement, and relation, with anomalies including both single-constraint and combined violations. We further propose a language-based anomaly detection framework that relies solely on text descriptions generated from normal images. Using contrastive learning with positive texts and contradiction-based negative texts synthesized from these descriptions, our method learns embeddings that capture logical attributes rather than low-level features. Extensive experiments demonstrate consistent improvements over baselines across the evaluated settings. The dataset is available at: https://github.com/nkthiroto/VID-AD.

Problem

• logical anomaly detection
• vision-induced distraction
• industrial inspection
• visual appearance variation
• rule-level violations

Innovation

• logical anomaly detection
• vision-induced distraction
• language-based anomaly detection
• contrastive learning
• industrial inspection