Table 3 Comparisons between two kinds of loss functions. \(\Delta\) indicates the improvements.
From: Weakly supervised learning through box annotations for pig instance segmentation
| Â | Box (%) | Mask (%) | ||||||
|---|---|---|---|---|---|---|---|---|
\(\textrm{AP}\) | \(\textrm{AP}_{0.5}\) | \(\textrm{AP}_{0.75}\) | \(\textrm{AP}_l\) | \(\textrm{AP}\) | \(\textrm{AP}_{0.5}\) | \(\textrm{AP}_{0.75}\) | \(\textrm{AP}_l\) | |
Original Loss | 87.89 | 96.90 | 93.62 | 89.60 | 82.66 | 97.05 | 94.89 | 85.35 |
Ours | 89.22 | 98.24 | 95.76 | 90.10 | 85.29 | 98.32 | 96.69 | 86.90 |
\(\Delta\) | +1.33 | +1.34 | +2.14 | +0.50 | +2.63 | +1.27 | +1.8 | +1.55 |
