Robust Novel Defect Detection with Neurosymbolic AI

Detecting novel product defects whose classes have not been seen at all during training time, is an important aspect of practical automated visual inspection in manufacturing. Without proper handling it is possible that these unknown defects will remain unnoticed causing production quality to deteriorate. Collecting more and more defect data is also not a solution as defects occur rarely in production and the ramp-up time of the AI-driven quality inspector becomes significantly slower. Since traditional machine algorithms are not always designed for handling these challenges, this paper applies an innovative approach based on Neurosymbolic AI. Specifically, we use a Logic Tensor Network that expresses the outputs of an unsupervised out-of-distribution detector as symbolic rules and uses them to drive the training of a neural network classifier. The resulting algorithm shows improved results in comparison to other related methods, especially in terms of defect recall, meaning that few defects remain undetected even if completely novel. More specifically, it achieves similar or better recall scores than semi-supervised and unsupervised methods when handling novel defects, but significantly outperforms them in defects that were seen during training. Similarly, when compared to supervised methods, it maintains high performance on known defects but significantly improves on novel ones. These best-of-both-worlds results are illustrated through higher F1-scores in the majority of the test datasets of manufacturing products.