ATAC-Net: Zoomed view works better for Anomaly Detection

arXiv:2406.14398v1 Announce Type: new
Abstract: The application of deep learning in visual anomaly detection has gained widespread popularity due to its potential use in quality control and manufacturing. Current standard methods are Unsupervised, where a clean dataset is utilised to detect deviations and flag anomalies during testing. However, incorporating a few samples when the type of anomalies is known beforehand can significantly enhance performance. Thus, we propose ATAC-Net, a framework that trains to detect anomalies from a minimal set of …

abstract anomaly anomaly detection application arxiv control cs.cv current dataset deep learning detection however manufacturing potential quality samples standard testing type unsupervised view visual