Skip to main content
. 2021 Dec 9;81(3):4475–4494. doi: 10.1007/s11042-021-11772-5

Table 4.

Ablation study of Yolov3

Backbone face face_mask mAP FPS
Darknet53-CIOU 90.82% 95.26% 93.04% 12.91
EfficientnetB2 75.64% 89.96% 82.80% 12.99
EfficientnetB2-Transer Learning 92.79% 97.23% 95.01% 13.08
EfficientnetB2-Transer Learning- CIOU 93.88% 98.18% 96.03% 14.62
EfficientnetB4-Transer Learning- CIOU 88.62% 94.86% 91.74% 11.87