mit-han-lab / spvnas

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
http://spvnas.mit.edu/
MIT License
588 stars 109 forks source link

A lightweight Cylinder3D model with much higher performance is now available!!! #96

Closed cardwing closed 2 years ago

cardwing commented 2 years ago

Recently, we have released a lightweight Cylinder3D model with much higher performance here. In this codebase, the reproduced Cylinder3D model is 2.9 point higher than the original Cylinder3D model in SemanticKITTI test set (single-scan). Besides, the released models achieve competitive performance in three benchmarks, i.e., ranks 1st in Waymo 3D Semantic Segmentation Challenge, ranks 1st in SemanticKITTI LiDAR Semantic Segmentation Challenge (single-scan) and ranks 2nd in SemanticKITTI LiDAR Semantic Segmentation Challenge (multi-scan). The trained model has been used in one NeurIPS 2022 submission! More LiDAR semantic segmentation models will be supported in the future. Do not hesitate to use the trained models!

zhijian-liu commented 2 years ago

Thanks for letting us know.

whu-lyh commented 2 years ago

???This operation is quite confusing..

lfl256 commented 2 years ago

@cardwing You have violated the rules of SemanticKITTI

https://github.com/cardwing/Codes-for-PVKD/issues/19 https://github.com/cardwing/Codes-for-PVKD/issues/18

According to SemanticKITTI's rules https://competitions.codalab.org/competitions/20331#learn_the_details-terms_and_conditions Important note: It is NOT allowed to register multiple times to the server using different email addresses. We are actively monitoring submissions and we will revoke access and delete submissions.