Question 1
My best network made use of Conv1D
layers and achieved an accuracy of 85.7%.
Here are some correct predictions.






Question 2
My best segmentation network had an accuracy of 80.0%, using an architecture similar to the classification network, but with a different output tensor shape. Here are some correct predictions:










Question 3
For the robustness analysis we conducted four experiments:
- Rotations of the input clouds
- Input different numbers of points
Rotations Test
For both models the procedure was the same: rotate the input data a certain amount and check the accuracy.Rotation in degrees (X, Y, Z) | Segmentation Accuracy | Classification Accuracy |
---|---|---|
(0, 0, 0) | 0.8001 | 0.8530 |
(30, 0, 0) | 0.7214 | 0.6568 |
(60, 0, 0) | 0.5989 | 0.3116 |
(90, 0, 0) | 0.4195 | 0.1689 |
(60, 0, 60) | 0.5614 | 0.3273 |
(30, 0, 80) | 0.5720 | 0.5089 |


Number of Points Test
For both the classification model and the segmentation model, the procedure was the same: Reduce the number of input points $N$ to the evaluation functions by callingpython eval_cls.py --num_points N
, python eval_seg.py --num_points N
.
Number of Points | Segmentation Accuracy | Classification Accuracy |
---|---|---|
10000 | 0.8001 | 0.8530 |
5000 | 0.8003 | 0.8436 |
1000 | 0.8005 | 0.8583 |
100 | 0.802 | 0.8583 |

