kyxt
/
code_test
Not watched
1
0
Fork 0
Code
Releases 0 Wiki evaluate Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain HPC
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
2 Commits
1 Branch
316 MB
19 Download
Tree: 500690453e
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '500690453e'
${ noResults }
code_test/configs/sabl/README.md

README.md 7.6 kB
Raw Normal View History

first commit
2 years ago
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
 12345678910111213141516171819202122232425262728293031323334353637 
  1. # Side-Aware Boundary Localization for More Precise Object Detection

  2. 

  3. ## Introduction

  4. 

  5. <!-- [ALGORITHM] -->

  6. 

  7. We provide config files to reproduce the object detection results in the ECCV 2020 Spotlight paper for [Side-Aware Boundary Localization for More Precise Object Detection](https://arxiv.org/abs/1912.04260).

  8. 

  9. ```latex

  10. @inproceedings{Wang_2020_ECCV,

  11.     title = {Side-Aware Boundary Localization for More Precise Object Detection},

  12.     author = {Jiaqi Wang and Wenwei Zhang and Yuhang Cao and Kai Chen and Jiangmiao Pang and Tao Gong and Jianping Shi and Chen Change Loy and Dahua Lin},

  13.     booktitle = {ECCV},

  14.     year = {2020}

  15. }

  16. ```

  17. 

  18. ## Results and Models

  19. 

  20. The results on COCO 2017 val is shown in the below table. (results on test-dev are usually slightly higher than val).

  21. Single-scale testing (1333x800) is adopted in all results.

  22. 

  23. |       Method       | Backbone  | Lr schd | ms-train | box AP |                                                       Config                                                       |                                                                                                                                   Download                                                                                                                                    |

  24. | :----------------: | :-------: | :-----: | :------: | :----: | :----------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |

  25. | SABL Faster R-CNN  | R-50-FPN  |   1x    |    N     |  39.9  |  [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_faster_rcnn_r50_fpn_1x_coco.py)  |    [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r50_fpn_1x_coco/sabl_faster_rcnn_r50_fpn_1x_coco-e867595b.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r50_fpn_1x_coco/20200830_130324.log.json)    |

  26. | SABL Faster R-CNN  | R-101-FPN |   1x    |    N     |  41.7  | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_faster_rcnn_r101_fpn_1x_coco.py)  |  [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r101_fpn_1x_coco/sabl_faster_rcnn_r101_fpn_1x_coco-f804c6c1.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_faster_rcnn_r101_fpn_1x_coco/20200830_183949.log.json)   |

  27. | SABL Cascade R-CNN | R-50-FPN  |   1x    |    N     |  41.6  | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_cascade_rcnn_r50_fpn_1x_coco.py)  |  [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_cascade_rcnn_r50_fpn_1x_coco/sabl_cascade_rcnn_r50_fpn_1x_coco-e1748e5e.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_cascade_rcnn_r50_fpn_1x_coco/20200831_033726.log.json)   |

  28. | SABL Cascade R-CNN | R-101-FPN |   1x    |    N     |  43.0  | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_cascade_rcnn_r101_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_cascade_rcnn_r101_fpn_1x_coco/sabl_cascade_rcnn_r101_fpn_1x_coco-2b83e87c.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_cascade_rcnn_r101_fpn_1x_coco/20200831_141745.log.json) |

  29. 

  30. |     Method     | Backbone  |  GN   | Lr schd |  ms-train   | box AP |                                                            Config                                                             |                                                                                                                                                    Download                                                                                                                                                    |

  31. | :------------: | :-------: | :---: | :-----: | :---------: | :----: | :---------------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |

  32. | SABL RetinaNet | R-50-FPN  |   N   |   1x    |      N      |  37.7  |        [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r50_fpn_1x_coco.py)         |                       [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_1x_coco/sabl_retinanet_r50_fpn_1x_coco-6c54fd4f.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_1x_coco/20200830_053451.log.json)                        |

  33. | SABL RetinaNet | R-50-FPN  |   Y   |   1x    |      N      |  38.8  |       [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r50_fpn_gn_1x_coco.py)       |                   [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_gn_1x_coco/sabl_retinanet_r50_fpn_gn_1x_coco-e16dfcf1.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r50_fpn_gn_1x_coco/20200831_141955.log.json)                   |

  34. | SABL RetinaNet | R-101-FPN |   N   |   1x    |      N      |  39.7  |        [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r101_fpn_1x_coco.py)        |                      [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_1x_coco/sabl_retinanet_r101_fpn_1x_coco-42026904.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_1x_coco/20200831_034256.log.json)                      |

  35. | SABL RetinaNet | R-101-FPN |   Y   |   1x    |      N      |  40.5  |      [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r101_fpn_gn_1x_coco.py)       |                 [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_1x_coco/sabl_retinanet_r101_fpn_gn_1x_coco-40a893e8.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_1x_coco/20200830_201422.log.json)                  |

  36. | SABL RetinaNet | R-101-FPN |   Y   |   2x    | Y (640~800) |  42.9  | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_640_800_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_640_800_coco/sabl_retinanet_r101_fpn_gn_2x_ms_640_800_coco-1e63382c.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_640_800_coco/20200830_144807.log.json) |

  37. | SABL RetinaNet | R-101-FPN |   Y   |   2x    | Y (480~960) |  43.6  | [config](https://github.com/open-mmlab/mmdetection/blob/master/configs/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco/sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco-5342f857.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/sabl/sabl_retinanet_r101_fpn_gn_2x_ms_480_960_coco/20200830_164537.log.json) |

No Description

Contributors (1)
All