Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Xiansheng Hua, Lei Zhang
This implementation is based on MMdetection. Please refer to install.md for detailed installation.
Please see getting_started.md for models training
and inference
.
Backbone | schd | Models | GPUs | AP | AP_25 | AP_50 | AP_70 | AP_75 |
---|---|---|---|---|---|---|---|---|
ResNet-50 | 3x | model | 4 | 36.5 | 76.8 | 64.2 | 44.8 | 36.4 |
ResNet-101 | 3x | model | 4 | 38.3 | 77.9 | 66.3 | 46.4 | 38.7 |
Backbone | schd | Models | GPUs | AP(val) | AP(test-dev) |
---|---|---|---|---|---|
ResNet-50 | 3x | model | 8 | 31.4 | 31.7 |
ResNet-101 | 3x | model | 8 | 33.0 | 33.4 |
ResNet-101-DCN | 3x | model | 8 | 35.0 | 35.4 |
Note:
- The following models are trained with Telsa V100 GPU.
- Following BBTP and DiscoBox, the Pascal VOC is aumented Pascal VOC(data link) with SBD. We recomment the users to train the Pascal VOC first to validate the performance with ~14 hours training time.
- Training COCO with 3x needs about 4 days.
- The pretrained models are in GoogleDriver.
Note: Please run the following script to get more visual results. The bounding box is generated by the mask prediction in the test results.
python tools/test.py configs/boxlevelset/config-xxx.py work_dirs/xxx.pth --show-dir show_dirs/
@article{li2022boxlevelset,
title={Box-supervised Instance Segmentation with Level Set Evolution},
author={Wentong Li, Wenyu Liu, Jianke Zhu, Miaomiao Cui, Xiansheng Hua, Lei Zhang},
journal={ECCV2022},
year={2022}
}
For academic use, this project is licensed under the Apache License 2.0. For commercial use, please contact the authors.