Table 1.
Algorithms | Supervision type | Proportion of labeled data for training | ||||
---|---|---|---|---|---|---|
5% | 10% | 20% | 50% | 100% | ||
Faster-RCNN | Supervised | 21.14 | 31.90 | 42.65 | 50.51 | 56.75 |
Semi-supervised | 29.33 | 40.14 | 49.20 | 53.19 | ||
FCOS | Supervised | 27.37 | 42.20 | 52.42 | 59.84 | 62.80 |
Semi-supervised | 38.17 | 47.93 | 55.79 | 61.32 |