Ablation studies on the mod level of the KITTI vol set for all classes 3D detection and all the results are evaluated with average precision and calculated by 40 recall positions.
| Experiments | FG | SSFT | DP | Car | Pedestrian | Cyclist |
|---|---|---|---|---|---|---|
| (1) | 84.87 | 59.87 | 73.23 | |||
| (2) | V | 85.08 | 59.91 | 73.02 | ||
| (3) | V | V | 85.34 | 60.30 | 74.33 | |
| (4) | V | V | V | 85.37 | 61.01 | 74.27 |
| Experiments | FG | SSFT | DP | Car | Pedestrian | Cyclist |
|---|---|---|---|---|---|---|
| (1) | 84.87 | 59.87 | 73.23 | |||
| (2) | V | 85.08 | 59.91 | 73.02 | ||
| (3) | V | V | 85.34 | 60.30 | 74.33 | |
| (4) | V | V | V | 85.37 | 61.01 | 74.27 |
Note: FG: foreground prediction network; SSFT: semantic-split feature transform; DP:discriminative RoI grid pooling.
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.