Benchmarking Unsupervised Anomaly Detection and Localization
It provides a systematic comparison to guide future research in a practical but incremental area of computer vision.
This paper conducts a comprehensive benchmarking of 13 existing methods for unsupervised anomaly detection and localization in computer vision, comparing performance and inference efficiency, and analyzes the MVTec AD dataset's label ambiguity while testing 2D methods on the new MVTec 3D-AD dataset.
Unsupervised anomaly detection and localization, as of one the most practical and challenging problems in computer vision, has received great attention in recent years. From the time the MVTec AD dataset was proposed to the present, new research methods that are constantly being proposed push its precision to saturation. It is the time to conduct a comprehensive comparison of existing methods to inspire further research. This paper extensively compares 13 papers in terms of the performance in unsupervised anomaly detection and localization tasks, and adds a comparison of inference efficiency previously ignored by the community. Meanwhile, analysis of the MVTec AD dataset are also given, especially the label ambiguity that affects the model fails to achieve full marks. Moreover, considering the proposal of the new MVTec 3D-AD dataset, this paper also conducts experiments using the existing state-of-the-art 2D methods on this new dataset, and reports the corresponding results with analysis.