Reconstruction-Based Anomaly Localization via Knowledge-Informed Self-Training

arXiv:2402.14246v1 Announce Type: new
Abstract: Anomaly localization, which involves localizing anomalous regions within images, is a significant industrial task. Reconstruction-based methods are widely adopted for anomaly localization because of their low complexity and high interpretability. Most existing reconstruction-based methods only use normal samples to construct model. If anomalous samples are appropriately utilized in the process of anomaly localization, the localization performance can be improved. However, usually only weakly labeled anomalous samples are available, which limits the improvement. In many cases, …

abstract anomaly arxiv complexity construct cs.cv cs.lg images industrial interpretability knowledge localization low normal samples self-training training type via