Table 4 Object detection results on validation set.
From: Visual imitation learning from one-shot demonstration for multi-step robot pick and place tasks
Classes | Images | Instances | Precision | Recall | mAP50 | mAP50-95 |
|---|---|---|---|---|---|---|
all | 3750 | 21821 | \(98.5\%\) | \(99\%\) | \(98.7\%\) | \(47.8\%\) |
GrayBox | 3750 | 3633 | \(98.8\%\) | \(99.1\%\) | \(98.6\%\) | \(43.4\%\) |
BlueBox | 3750 | 3670 | \(98.7\%\) | \(99.3\%\) | \(99\%\) | \(48.4\%\) |
Parallelogram | 3750 | 3637 | \(98.3\%\) | \(97.4\%\) | \(98.4\%\) | \(48.3\%\) |
Cuboid | 3750 | 3598 | \(96.8\%\) | \(99.4\%\) | \(98.4\%\) | \(48.4\%\) |
Octagon | 3750 | 3652 | \(99.1\%\) | \(99.3\%\) | \(98.7\%\) | \(48.6\%\) |
Star | 3750 | 3631 | \(99.3\%\) | \(99.3\%\) | \(99\%\) | \(49.6\%\) |
