Table 7 Metrics for each pathology type (YOLOv8l-seg).
From: Deep learning-driven pathology detection and analysis in historic masonry buildings of Suzhou
Class | Images | Instances | Box | Mask | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
Precision | Recall | mAP50 | mAP50-95 | Precision | Recall | mAP50 | mAP50-95 | |||
all | 174 | 1963 | 0.621 | 0.497 | 0.545 | 0.302 | 0.603 | 0.489 | 0.518 | 0.278 |
ML | 3 | 23 | 0.657 | 0.783 | 0.78 | 0.363 | 0.655 | 0.783 | 0.78 | 0.436 |
DD | 148 | 1001 | 0.495 | 0.518 | 0.471 | 0.324 | 0.488 | 0.514 | 0.45 | 0.288 |
CR | 59 | 144 | 0.58 | 0.41 | 0.483 | 0.266 | 0.548 | 0.389 | 0.456 | 0.17 |
SS | 137 | 746 | 0.612 | 0.45 | 0.522 | 0.359 | 0.611 | 0.453 | 0.516 | 0.333 |
BI | 20 | 49 | 0.762 | 0.326 | 0.468 | 0.199 | 0.712 | 0.306 | 0.386 | 0.164 |
