Awesome

Train in Germany, Test in The USA: Making 3D Object Detectors Generalize

This paper has been accpeted by Conference on Computer Vision and Pattern Recognition (CVPR) 2020.

Train in Germany, Test in The USA: Making 3D Object Detectors Generalize

by Yan Wang*, Xiangyu Chen*, Yurong You, Li Erran, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao*

Dependencies

Usage

Prepare Datasets (Jupyter notebook)

We develop our method on these datasets:

Configure dataset_path in config_path.py.

Raw datasets will be organized as the following structure:
<pre> dataset_path/ | kitti/ # KITTI object detection 3D dataset | training/ | testing/ | argo/ # Argoverse dataset v1.1 | train1/ | train2/ | train3/ | train4/ | val/ | test/ | nusc/ # nuScenes dataset v1.0 | maps/ | samples/ | sweeps/ | v1.0-trainval/ | lyft/ # Lyft Level 5 dataset v1.02 | v1.02-train/ | waymo/ # Waymo dataset v1.0 | training/ | validation/ </pre>
Download all datasets.

For KITTI, Argoverse and Waymo, we provide scripts for automatic download.
```
cd scripts/
python download.py [--datasets kitti+argo+waymo]
```
nuScenes and Lyft need to downloaded manually.

Convert all datasets to KITTI format.

cd scripts/
python -m pip install -r convert_requirements.txt
python convert.py [--datasets argo+nusc+lyft+waymo]

Split validation set

We provide the train/val split used in our experiments under split folder.
```
cd split/
python replace_split.py
```
Generate car subset

We filter scenes and only keep those with cars.
```
cd scripts/
python gen_car_split.py
```

Statistical Normalization (Jupyter notebook)

Compute car size statistics of each dataset. The computed statistics are stored as label_stats_{train/val/test}.json under KITTI format dataset root.
```
cd stat_norm/
python stat.py
```
Generate rescaled datasets according to car size statistics. The rescaled datasets are stored under $dataset_path/rescaled_datasets by default.
```
cd stat_norm/
python norm.py [--path $PATH]
```

Training (To be updated)

We use PointRCNN to validate our method.

Setup PointRCNN
```
cd pointrcnn/
./build_and_install.sh
```
Build datasets in PointRCNN format.
```
cd pointrcnn/tools/
python generate_multi_data.py
python generate_gt_database.py --root ...
```
The NuScence dataset has much less points in each bounding box, so we have to turn of the GT_AUG_HARD_RATIO augmentation.
Download the models pretrained on source domains from google drive using gdrive.
```
cd pointrcnn/tools/
gdrive download -r 14MXjNImFoS2P7YprLNpSmFBsvxf5J2Kw
```

Adapt to a new domain by re-training with rescaled data.

cd pointrcnn/tools/

python train_rcnn.py --cfg_file ...

Inference

cd pointrcnn/tools/
python eval_rcnn.py --ckpt /path/to/checkpoint.pth --dataset $dataset --output_dir $output_dir

Evaluation

We provide evaluation code with

old (based on bbox height) and new (based on distance) difficulty metrics
<em>output transformation</em> functions to locate domain gap

python evaluate/
python evaluate.py --result_path $predictions --dataset_path $dataset_root --metric [old/new]

Citation

@inproceedings{wang2020train,
  title={Train in germany, test in the usa: Making 3d object detectors generalize},
  author={Yan Wang and Xiangyu Chen and Yurong You and Li Erran and Bharath Hariharan and Mark Campbell and Kilian Q. Weinberger and Wei-Lun Chao},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={11713-11723},
  year={2020}
}