A Comprehensive Augmentation Framework for Anomaly Detection
This work addresses the challenge of generalizing anomaly detection models to diverse real-world anomalies, though it appears incremental as it builds on existing augmentation and reconstruction methods.
The paper tackles the problem of biased training distributions in anomaly detection by developing a comprehensive augmentation framework that considers class-specific anomaly standards and integrates with reconstruction-based approaches, achieving state-of-the-art performance on the MVTec dataset with particular improvements in object classes.
Data augmentation methods are commonly integrated into the training of anomaly detection models. Previous approaches have primarily focused on replicating real-world anomalies or enhancing diversity, without considering that the standard of anomaly varies across different classes, potentially leading to a biased training distribution. This paper analyzes crucial traits of simulated anomalies that contribute to the training of reconstructive networks and condenses them into several methods, thus creating a comprehensive framework by selectively utilizing appropriate combinations. Furthermore, we integrate this framework with a reconstruction-based approach and concurrently propose a split training strategy that alleviates the issue of overfitting while avoiding introducing interference to the reconstruction process. The evaluations conducted on the MVTec anomaly detection dataset demonstrate that our method outperforms the previous state-of-the-art approach, particularly in terms of object classes. To evaluate generalizability, we generate a simulated dataset comprising anomalies with diverse characteristics since the original test samples only include specific types of anomalies and may lead to biased evaluations. Experimental results demonstrate that our approach exhibits promising potential for generalizing effectively to various unforeseen anomalies encountered in real-world scenarios.