Towards High-Resolution Industrial Image Anomaly Detection

TL;DR

This paper introduces HiAD, a novel high-resolution anomaly detection framework that effectively captures subtle and large anomalies in industrial images while maintaining computational efficiency.

Contribution

HiAD employs a dual-branch architecture with multi-resolution feature fusion and an adaptive detector pool, advancing high-resolution anomaly detection in industrial scenarios.

Findings

Outperforms existing methods on MVTec-HD, VisA-HD, and RealIAD-HD benchmarks.

Effectively detects anomalies of varying sizes in high-resolution images.

Maintains high detection accuracy with limited computational resources.

Abstract

Current anomaly detection methods primarily focus on low-resolution scenarios. For high-resolution images, conventional downsampling often results in missed detections of subtle anomalous regions due to the loss of fine-grained discriminative information. Despite some progress, recent studies have attempted to improve detection resolution by employing lightweight networks or using simple image tiling and ensemble methods. However, these approaches still struggle to meet the practical demands of industrial scenarios in terms of detection accuracy and efficiency. To address the above issues, we propose HiAD, a general framework for high-resolution anomaly detection. HiAD is capable of detecting anomalous regions of varying sizes in high-resolution images under limited computational resources. Specifically, HiAD employs a dual-branch architecture that integrates anomaly cues across different scales to comprehensively capture both subtle and large-scale anomalies. Furthermore, it incorporates a multi-resolution feature fusion strategy to tackle the challenges posed by fine-grained texture variations in high-resolution images. To enhance both adaptability and efficiency, HiAD utilizes a detector pool in conjunction with various detector assignment strategies, enabling detectors to be adaptively assigned based on patch features, ensuring detection performance while effectively controlling computational costs. We conduct extensive experiments on our specifically constructed high-resolution anomaly detection benchmarks, including MVTec-HD, VisA-HD, and the real-world benchmark RealIAD-HD, demonstrating the superior performance of HiAD. The code is available at https://github.com/cnulab/HiAD.