Neural Architecture Search for Visual Anomaly Segmentation. (arXiv:2304.08975v3 [cs.CV] UPDATED)

This paper presents the first application of neural architecture search to
the complex task of segmenting visual anomalies. Measurement of anomaly
segmentation performance is challenging due to imbalanced anomaly pixels,
varying region areas, and various types of anomalies. First, the
region-weighted Average Precision (rwAP) metric is proposed as an alternative
to existing metrics, which does not need to be limited to a specific maximum
false positive rate. Second, the AutoPatch neural architecture search method is
proposed, which enables efficient segmentation …

anomaly application architecture arxiv measurement neural architecture search paper performance pixels precision search segmentation types