Dayong Ren, Zhe Ma, Yuanpei Chen, Weihang Peng, Xiaode Liu, Yuhan Zhang, Yufei Guo
We lifted 10 functions out of this paper's own repositories and ran 7 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 |
|---|---|---|
| DayongRen/Spiking-PointNet | canonical | 0 of 1 |
| dayongren/spiking-pointnet | — | 7 of 8 |
| copy not recorded | — | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| LIFAct | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("53e8918bc52236f1") |
| SpikeBatchNorm | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("e7008a5cae4666f4") |
| SpikeConv | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("1e7782123767ff49") |
| SpikeLinear | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("58daf7e76a59d9df") |
| SpikeModel | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("c494ea8e2c450547") |
| mem_update | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("3feff0fd15c37746") |
| spike_activation | Ran | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("cbe6b782dd0724b0") |
| SpikeModule | Not yet run | dayongren/spiking-pointnet/models/spike_model.py code served (permissive licence) · get_code("4a02254778236267") |
| test | Not yet run | DayongRen/Spiking-PointNet/test_classification.py code served (permissive licence) · get_code("290bbfb3d5c4811c") |
| test | Not yet run | this paper's copy was not recorded; identical code first harvested from yanx27/pointnet_pointnet2_pytorch pointer only · get_code("cce988c817575a1a") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Recently, Spiking Neural Networks (SNNs), enjoying extreme energy efficiency, have drawn much research attention on 2D visual recognition and shown gradually increasing application potential. However, it still remains underexplored whether SNNs can be generalized to 3D recognition. To this end, we present Spiking PointNet in the paper, the first spiking neural model for efficient deep learning on point clouds. We discover that the two huge obstacles limiting the application of SNNs in point clouds are: the intrinsic optimization obstacle of SNNs that impedes the training of a big spiking model with large time steps, and the expensive memory and computation cost of PointNet that makes training a big spiking point model unrealistic. To solve the problems simultaneously, we present a trained-less but learning-more paradigm for Spiking PointNet with theoretical justifications and in-depth experimental analysis. In specific, our Spiking PointNet is trained with only a single time step but can obtain better performance with multiple time steps inference, compared to the one trained directly with multiple time steps. We conduct various experiments on ModelNet10, ModelNet40 to demonstrate the effectiveness of Spiking PointNet. Notably, our Spiking PointNet even can outperform its ANN counterpart, which is rare in the SNN field thus providing a potential research direction for the following work. Moreover, Spiking PointNet shows impressive speedup and storage saving in the training phase. Our code is open-sourced at Spiking-PointNet.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.06232")
get_code_for_paper("2310.06232")
have("2310.06232")
Connect an agent — have() is free.