Results for MinkowskiNet
Submission data
| Full name | MinkowskiNet |
| Description | We used the 3D variant of the 4D MinkowskiNet34, which consists of 42 (34 + 8) convolution layers and was trained for 120k iterations.
Next, we train the network from LR=1e-2 on both train+val set for another 120k iterations. For implementation, we used the Minkowski Engine (https://github.com/StanfordVL/MinkowskiEngine). |
| Publication title | 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks |
| Publication authors | C. Choy, J. Gwak, S. Savarese |
| Publication venue | CVPR 2019 |
| Publication URL | https://arxiv.org/abs/1904.08755 |
| Input Data Types | Uses Color Uses 3D |
| Programming language(s) | python/pytorch/C++/CUDA |
| Hardware | TitanRTX |
| Website | https://github.com/chrischoy/SpatioTemporalSegmentation |
| Source code or download URL | https://github.com/chrischoy/SpatioTemporalSegmentation |
| Submission creation date | 27 Oct, 2018 |
| Last edited | 1 Oct, 2019 |
3D semantic label results
| Info | avg iou | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | floor | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | wall | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 | 0.736 | 0.859 | 0.818 | 0.832 | 0.709 | 0.840 | 0.521 | 0.853 | 0.660 | 0.643 | 0.951 | 0.544 | 0.286 | 0.731 | 0.893 | 0.675 | 0.772 | 0.683 | 0.874 | 0.852 | 0.727 |