MaochengHu 576cda45b8 first commit | 2 years ago | |
---|---|---|
.. | ||
_base_ | 2 years ago | |
README.md | 2 years ago | |
gfl_r101vd_fpn_mstrain_2x_coco.yml | 2 years ago | |
gfl_r18vd_1x_coco.yml | 2 years ago | |
gfl_r34vd_1x_coco.yml | 2 years ago | |
gfl_r50_fpn_1x_coco.yml | 2 years ago | |
gflv2_r50_fpn_1x_coco.yml | 2 years ago |
We reproduce the object detection results in the paper Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection and Generalized Focal Loss V2. And We use a better performing pre-trained model and ResNet-vd structure to improve mAP.
Backbone | Model | batch-size/GPU | lr schedule | FPS | Box AP | download | config |
---|---|---|---|---|---|---|---|
ResNet50 | GFL | 2 | 1x | ---- | 41.0 | model | log | config |
ResNet101-vd | GFL | 2 | 2x | ---- | 46.8 | model | log | config |
ResNet34-vd | GFL | 2 | 1x | ---- | 40.8 | model | log | config |
ResNet18-vd | GFL | 2 | 1x | ---- | 36.6 | model | log | config |
ResNet50 | GFLv2 | 2 | 1x | ---- | 41.2 | model | log | config |
Notes:
mAP(IoU=0.5:0.95)
.@article{li2020generalized,
title={Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection},
author={Li, Xiang and Wang, Wenhai and Wu, Lijun and Chen, Shuo and Hu, Xiaolin and Li, Jun and Tang, Jinhui and Yang, Jian},
journal={arXiv preprint arXiv:2006.04388},
year={2020}
}
@article{li2020gflv2,
title={Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection},
author={Li, Xiang and Wang, Wenhai and Hu, Xiaolin and Li, Jun and Tang, Jinhui and Yang, Jian},
journal={arXiv preprint arXiv:2011.12885},
year={2020}
}