- Notifications
You must be signed in to change notification settings - Fork6
qcraftai/distill-bev
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Zeyu Wang,Dingwen Li,Chenxu Luo,Cihang Xie,Xiaodong Yang
DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation, ICCV 2023
Please refer toINSTALL to set up the environment and install the dependencies (see more details inDockerfile).
Please follow the instructions inDATA.
Please follow the instructions inRUN.
BEVDepth and BEVFormer are respectively used in this repo as CNNs and Transformers based students to exemplify the improvement by DistillBEV.
- Backbone: ResNet-50 pre-trained on ImageNet-1K
| Teacher | Student | mAP | NDS | Checkpoints |
|---|---|---|---|---|
| - | BEVDepth | 36.4 | 48.4 | [Google Drive] [Baidu Cloud] |
| CenterPoint | BEVDepth | 39.0 | 50.6 | [Google Drive] [Baidu Cloud] |
| MVP | BEVDepth | 40.3 | 51.0 | [Google Drive] [Baidu Cloud] |
| Teacher | Student | mAP | NDS | Checkpoints |
|---|---|---|---|---|
| - | BEVFormer | 32.3 | 43.4 | [Google Drive] [Baidu Cloud] |
| CenterPoint | BEVFormer | 35.9 | 46.8 | [Google Drive] [Baidu Cloud] |
| MVP | BEVFormer | 36.7 | 47.6 | [Google Drive] [Baidu Cloud] |
- Backbone: ResNet-101 pre-trained on ImageNet-1K
| Teacher | Student | mAP | NDS | Checkpoints |
|---|---|---|---|---|
| - | BEVDepth | 40.7 | 52.2 | [Google Drive] [Baidu Cloud] |
| CenterPoint | BEVDepth | 43.6 | 53.6 | [Google Drive] [Baidu Cloud] |
| MVP | BEVDepth | 45.0 | 54.6 | [Google Drive] [Baidu Cloud] |
| Teacher | Student | mAP | NDS | Checkpoints |
|---|---|---|---|---|
| - | BEVFormer | 34.9 | 46.0 | [Google Drive] [Baidu Cloud] |
| CenterPoint | BEVFormer | 37.4 | 48.2 | [Google Drive] [Baidu Cloud] |
| MVP | BEVFormer | 38.2 | 49.1 | [Google Drive] [Baidu Cloud] |
Please cite the following paper if this repo helps your research:
@InProceedings{Wang_2023_ICCV, author = {Wang, Zeyu and Li, Dingwen and Luo, Chenxu and Xie, Cihang and Yang, Xiaodong}, title = {DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation}, booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023},}We thank the authors for the multiple great open-sourced repos, includingMMDetection3D,CenterPoint,BEVDet,BEVDepth andBEVFormer.
Copyright (C) 2023 QCraft. All rights reserved. Licensed under theCC BY-NC-SA 4.0 (Attribution-NonCommercial-ShareAlike 4.0 International). The code is released for academic research use only. For commercial use, please contactbusiness@qcraft.ai.