Results for One Thing One Click
Submission data
| Full name | A Self Training Approach for Weakly Supervised 3D Semantic Segmentation |
| Description | Only 0.02% of all the labels are used to train the model |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | C++, CUDA, Python |
| Hardware | RTX 2080Ti |
| Submission creation date | 13 Mar, 2021 |
| Last edited | 14 Mar, 2021 |
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.701 | 0.825 | 0.796 | 0.723 | 0.716 | 0.832 | 0.433 | 0.816 | 0.634 | 0.609 | 0.969 | 0.418 | 0.344 | 0.559 | 0.833 | 0.715 | 0.808 | 0.560 | 0.902 | 0.847 | 0.680 |