Cross-Modal BEV Distillation for Multi-View 3D Object Detection
Zehui Chen, Zhenyu Li, Shiquan Zhang, Liangji Fang, Qinhong Jiang, Feng Zhao.
This code is an initial release with BEVFormer-T only, we will release a full version in the future.
# baseline
./tools/dist_train.sh projects/configs/video_bevformer/bevformer_128x128_r50_2x.py 8
# BEVDistill
./tools/dist_train_distill.sh projects/configs/bevdistill/bevdistill_r50_128x128_900query_bboxrweighttop100_bevgt_mocov2_merge_r1_2x.py 8
Model |
config |
mAP |
NDS |
BEVFormer-R50 |
|
35.2 |
42.3 |
BEVDistill-R50 |
|
38.6 |
45.7 |
BEVFormer-T-R50 |
link |
38.3 |
48.8 |
BEVDistill-T-R50 |
link |
40.7 |
51.5 |
BEVFormer-T-R101 |
link |
40.5 |
50.6 |
BEVDistill-T-R101 |
link |
41.7 |
52.4 |
Model |
Weight |
mAP |
NDS |
ObjectDGCNN (Teacher) |
link |
67.4 |
61.5 |
FCOS3D r50 (Student) |
link |
|
|