We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| plusmultiply/mprm | canonical | 4 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| IoU_class_metrics | Ran | plusmultiply/mprm/plot_convergence_mprm.py code served (permissive licence) · get_code("814a2fe9241bee1e") |
| IoU_multi_metrics | Ran | plusmultiply/mprm/plot_convergence_mprm.py code served (permissive licence) · get_code("09d5696850a35aee") |
| bias_variable | Ran | plusmultiply/mprm/models/network_blocks_mprm.py code served (permissive licence) · get_code("6a88f1ae24fa26b2") |
| running_mean | Ran | plusmultiply/mprm/plot_convergence_mprm.py code served (permissive licence) · get_code("2e38027f9a1a89e6") |
| ind_max_pool | Not yet run | plusmultiply/mprm/models/network_blocks_mprm.py code served (permissive licence) · get_code("4383ecd8cc0719fa") |
| weight_variable | Not yet run | plusmultiply/mprm/models/network_blocks_mprm.py code served (permissive licence) · get_code("5a6188c7d118c3fc") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumbersome process. However, manually producing point-level label on the large scale dataset is time and labor-intensive. In this paper, we propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. We introduce our multi-path region mining module to generate pseudo point-level label from a classification network trained with weak labels. It mines the localization cues for each class from various aspects of the network feature using different attention modules. Then, we use the point-level pseudo labels to train a point cloud segmentation network in a fully supervised manner. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network. In our setting, the 3D weak labels only indicate the classes that appeared in our input sample. We discuss both scene- and subcloud-level weakly labels on raw 3D point cloud data and perform in-depth experiments on them. On ScanNet dataset, our result trained with subcloud-level labels is compatible with some fully supervised methods.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2003.13035")
get_code_for_paper("2003.13035")
have("2003.13035")
Connect an agent — have() is free.