Find defects in part images when only train with defect-free images
Find defects in part images when only train with defect-free images
Towards Total Recall in Industrial Anomaly Detection
arXiv paper abstract https://arxiv.org/abs/2106.08265v1
arXiv PDF paper https://arxiv.org/pdf/2106.08265v1.pdf
Papers With Code https://paperswithcode.com/paper/towards-total-recall-in-industrial-anomaly
Being able to spot defective parts is a critical component in large-scale industrial manufacturing.
… challenge that we address … fit a model using nominal (non-defective) example images only.
… goal is to build systems that work well simultaneously on many different tasks automatically.
… propose PatchCore, which uses a maximally representative memory bank of nominal patch-features.
… competitive inference times while achieving state-of-the-art performance for both detection and localization.
On the standard dataset MVTec AD, PatchCore achieves an image-level anomaly detection AUROC score of 99.1%, more than halving the error compared to the next best competitor. …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
