Robust Defect Detection with Contrastive Localization

Defect detection aims to detect and localize regions out of the normal distribution. Previous works rely on modeling the normality to identify the defective regions, which may lead to non-ideal generalizability. This paper proposed a one-stage framework that detects defective patterns directly without the modeling process. This ability is adopted through the joint efforts of three parties: a generative adversarial network (GAN), a newly proposed scaled pattern loss, and a dynamic masked cycle-consistent auxiliary network. Explicit information that could indicate the position of defects is intentionally excluded to avoid learning any direct mapping. Experimental results on the texture class of the challenging MVTec AD dataset show that the proposed method is 2.9\% higher than the SOTA methods in F1-Score, while substantially outperforming SOTA methods in generalizability.