Table 3 Accuracy of the baseline model’s object detection and image segmentation tasks
From: Pest detection in dynamic environments: an adaptive continual test-time domain adaptation strategy
Original environment | Precision\(\uparrow\) | Recall\(\uparrow\) | mAP50\(\uparrow\) | mAP50-95\(\uparrow\) |
|---|---|---|---|---|
YOLOv9c | 0.681 | 0.671 | 0.714 | 0.481 |
YOLOv9e | 0.658 | 0.701 | 0.733 | 0.496 |
YOLOv9c-seg | 0.613 | 0.606 | 0.607 | 0.507 |
YOLOv9e-seg | 0.623 | 0.613 | 0.611 | 0.511 |
Target environment | Precision\(\uparrow\) | Recall\(\uparrow\) | mAP50\(\uparrow\) | mAP50-95\(\uparrow\) |
|---|---|---|---|---|
YOLOv9c | 0.431 | 0.402 | 0.376 | 0.239 |
YOLOv9e | 0.457 | 0.53 | 0.481 | 0.313 |
YOLOv9c-seg | 0.478 | 0.366 | 0.362 | 0.291 |
YOLOv9e-seg | 0.461 | 0.415 | 0.399 | 0.321 |