Online Prototype Memory Enhances Unsupervised Industrial Anomaly Detection
Researchers developed an online prototype memory framework that improves unsupervised industrial anomaly detection while reducing stored patch embeddings.
Researchers developed an online prototype memory framework that improves unsupervised industrial anomaly detection while reducing stored patch embeddings.
A compact neural network architecture combines local receptive fields, lateral inhibition, and feature-space reconstruction to deliver competitive industrial anomaly detection ...
Researchers at Shiv Nadar University have developed a dual-path AI framework that combines a residual gated autoencoder with patchwise nearest-neighbor ...
Researchers at Yonsei University have developed a prompt-tuning method that lets the vision-language model CLIP detect and localize industrial defects ...
A new cross-modal AI framework called CMAC-Net aligns visual defect regions with textual semantics, improving industrial anomaly detection accuracy and ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine