CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks. (arXiv:2206.01992v3 [cs.CV] UPDATED)

Detection of object anomalies is crucial in industrial processes, but
unsupervised anomaly detection and localization is particularly important due
to the difficulty of obtaining a large number of defective samples and the
unpredictable types of anomalies in real life. Among the existing unsupervised
anomaly detection and localization methods, the NF-based scheme has achieved
better results. However, the two subnets (complex functions) $s_{i}(u_{i})$ and
$t_{i}(u_{i})$ in NF are usually multilayer perceptrons, which need to squeeze
the input visual features from 2D …

anomaly anomaly detection arxiv attention cv detection flow localization networks neural networks