Table 9.
Baseline | WIoU v3 | BiFormer | B1-FFNB | B2-FFNB | Precision/% | Recall/% | mAP0.5/% | mAP0.5:0.95/% | Model Size/MB | Detection Time/ms | Parameter/106 |
---|---|---|---|---|---|---|---|---|---|---|---|
YOLOv8s | 50.9 | 38.2 | 39.3 | 23.5 | 22.5 | 7.7 | 11.1 | ||||
√ | 50.7 | 38.7 | 40.0 | 23.6 | 22.5 | 7.2 | 11.1 | ||||
√ | √ | 50.6 | 39.2 | 40.5 | 24.1 | 22.1 | 7.8 | 10.9 | |||
√ | √ | √ | 55.8 | 42.8 | 44.8 | 27.2 | 21.6 | 11.2 | 10.6 | ||
√ | √ | √ | √ | 54.4 | 45.6 | 47.0 | 29.2 | 21.5 | 19.5 | 10.3 |