Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era

TL;DR

This paper introduces Real-IAD Variety, the largest and most diverse industrial anomaly detection dataset, designed to challenge and advance the development of robust, scalable IAD algorithms across numerous real-world industrial scenarios.

Contribution

It presents the Real-IAD Variety dataset, significantly expanding category diversity and scale, and analyzes the performance of various IAD models on this new benchmark.

Findings

State-of-the-art methods degrade by 10-20% with increased categories.

Zero-shot and few-shot models maintain stable performance across categories.

The dataset enables more realistic evaluation of IAD algorithms.

Abstract

Industrial Anomaly Detection (IAD) is a cornerstone for ensuring operational safety, maintaining product quality, and optimizing manufacturing efficiency. However, the advancement of IAD algorithms is severely hindered by the limitations of existing public benchmarks. Current datasets often suffer from restricted category diversity and insufficient scale, leading to performance saturation and poor model transferability in complex, real-world scenarios. To bridge this gap, we introduce Real-IAD Variety, the largest and most diverse IAD benchmark. It comprises 198,950 high-resolution images across 160 distinct object categories. The dataset ensures unprecedented diversity by covering 28 industries, 24 material types, 22 color variations, and 27 defect types. Our extensive experimental analysis highlights the substantial challenges posed by this benchmark: state-of-the-art multi-class unsupervised anomaly detection methods suffer significant performance degradation (ranging from 10% to 20%) when scaled from 30 to 160 categories. Conversely, we demonstrate that zero-shot and few-shot IAD models exhibit remarkable robustness to category scale-up, maintaining consistent performance and significantly enhancing generalization across diverse industrial contexts. This unprecedented scale positions Real-IAD Variety as an essential resource for training and evaluating next-generation foundation IAD models.