ADNet: A Large-Scale and Extensible Multi-Domain Benchmark for Anomaly Detection Across 380 Real-World Categories

TL;DR

ADNet introduces a comprehensive large-scale benchmark with 380 categories across multiple domains, highlighting scalability challenges in anomaly detection and proposing a Mixture-of-Experts model to improve performance.

Contribution

The paper presents ADNet, a new extensive multi-domain benchmark for anomaly detection, and proposes Dinomaly-m, a scalable model that enhances detection accuracy across many categories.

Findings

Existing methods drop in performance when scaling to 380 categories.

Dinomaly-m outperforms previous models with 83.2% I-AUROC.

ADNet provides a standardized platform for future anomaly detection research.

Abstract

Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range of categories, limiting the evaluation of cross-context generalization and scalability. We introduce ADNet, a large-scale, multi-domain benchmark comprising 380 categories aggregated from 49 publicly available datasets across Electronics, Industry, Agrifood, Infrastructure, and Medical domains. The benchmark includes a total of 196,294 RGB images, consisting of 116,192 normal samples for training and 80,102 test images, of which 60,311 are anomalous. All images are standardized with MVTec-style pixel-level annotations and structured text descriptions spanning both spatial and visual attributes, enabling multimodal anomaly detection tasks. Extensive experiments reveal a clear scalability challenge: existing state-of-the-art methods achieve 90.6% I-AUROC in one-for-one settings but drop to 78.5% when scaling to all 380 categories in a multi-class setting. To address this, we propose Dinomaly-m, a context-guided Mixture-of-Experts extension of Dinomaly that expands decoder capacity without increasing inference cost. It achieves 83.2% I-AUROC and 93.1% P-AUROC, demonstrating superior performance over existing approaches. ADNet is designed as a standardized and extensible benchmark, supporting the community in expanding anomaly detection datasets across diverse domains and providing a scalable foundation for future anomaly detection foundation models. Dataset: https://grainnet.github.io/ADNet