Table 7 Plankton cell center detection accuracy in terms of mAP. EfficientNetb1 is used as backbone for the 4 neural networks implemented in VisionTool.
From: A semi-automatic toolbox for markerless effective semantic feature extraction
Net/Backbone | mAP\(^{0.5}\) | mAP\(^{0.75}\) | mAP |
|---|---|---|---|
FPN/Efficientb1 | 0.980 | 0.919 | 0.908 |
LinkNet/Efficientb1 | 0.951 | 0.837 | 0.839 |
PSPNet/Efficientb1 | 0.942 | 0.776 | 0.784 |
Unet/Efficientb1 | 0.976 | 0.919 | 0.907 |
