Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial Applications

TL;DR

Multi-AD is a novel CNN-based unsupervised anomaly detection framework that leverages attention mechanisms, knowledge distillation, and multi-scale features to effectively identify anomalies across diverse medical and industrial image domains.

Contribution

The paper introduces Multi-AD, a cross-domain unsupervised anomaly detection model combining SE blocks, knowledge distillation, and multi-scale features for improved detection accuracy.

Findings

Achieved state-of-the-art AUROC scores on medical and industrial datasets.

Demonstrated strong generalization across multiple domains.

Outperformed existing models in both image-level and pixel-level anomaly detection.

Abstract

Traditional deep learning models often lack annotated data, especially in cross-domain applications such as anomaly detection, which is critical for early disease diagnosis in medicine and defect detection in industry. To address this challenge, we propose Multi-AD, a convolutional neural network (CNN) model for robust unsupervised anomaly detection across medical and industrial images. Our approach employs the squeeze-and-excitation (SE) block to enhance feature extraction via channel-wise attention, enabling the model to focus on the most relevant features and detect subtle anomalies. Knowledge distillation (KD) transfers informative features from the teacher to the student model, enabling effective learning of the differences between normal and anomalous data. Then, the discriminator network further enhances the model's capacity to distinguish between normal and anomalous data. At the inference stage, by integrating multi-scale features, the student model can detect anomalies of varying sizes. The teacher-student (T-S) architecture ensures consistent representation of high-dimensional features while adapting them to enhance anomaly detection. Multi-AD was evaluated on several medical datasets, including brain MRI, liver CT, and retina OCT, as well as industrial datasets, such as MVTec AD, demonstrating strong generalization across multiple domains. Experimental results demonstrated that our approach consistently outperformed state-of-the-art models, achieving the best average AUROC for both image-level (81.4% for medical and 99.6% for industrial) and pixel-level (97.0% for medical and 98.4% for industrial) tasks, making it effective for real-world applications.