ObjectCore - Efficient Few-shot Logical Anomaly Detection using Object Representations

Anomaly Detection is an important problem in industrial processes. Two new subfields have recently emerged: logical anomaly detection and few-shot anomaly detection. The combined task, few-shot logical anomaly detection, has proven exceptionally difficult and highly important for industrial processes. Few-shot methods use suboptimal representations to model composition information necessary for detecting logical anomalies, and previous full-shot methods require a large training set. To solve both problems, we propose ObjectCore, a few-shot logical anomaly detection model that captures the composition information from only a few images without any category-specific information. The composition information of an image is modelled as a collection of object representations. Logical anomalies are detected using bipartite matching between object representations in the test image and object representations in the most similar support image. ObjectCore significantly improves over state-of-the-art methods on two standard benchmarks for few-shot logical anomaly detection, MVTec LOCO and CAD-SD, attaining an image-level AUROC of 80.8% and 96.5%, respectively, in the 4-shot setting. Code: https://github.com/MaticFuc/ObjectCore