Supervised Anomaly Detection for Complex Industrial Images

arXiv:2405.04953v1 Announce Type: cross
Abstract: Automating visual inspection in industrial production lines is essential for increasing product quality across various industries. Anomaly detection (AD) methods serve as robust tools for this purpose. However, existing public datasets primarily consist of images without anomalies, limiting the practical application of AD methods in production settings. To address this challenge, we present (1) the Valeo Anomaly Dataset (VAD), a novel real-world industrial dataset comprising 5000 images, including 2000 instances of challenging real defects across …

abstract anomaly anomaly detection application arxiv cs.cv cs.lg datasets detection however images industrial industries inspection practical product production public quality robust serve tools type visual visual inspection