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.
9 Commits
1 Branch
316 MB
15 Download
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
code_test/configs/pisa/README.md

README.md 4.8 kB
Raw Permalink Normal View History

first commit
2 years ago
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
​
 12345678910111213141516171819202122232425262728293031323334353637383940 
  1. # Prime Sample Attention in Object Detection

  2. 

  3. ## Introduction

  4. 

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

  6. 

  7. ```latex

  8. @inproceedings{cao2019prime,

  9.   title={Prime sample attention in object detection},

  10.   author={Cao, Yuhang and Chen, Kai and Loy, Chen Change and Lin, Dahua},

  11.   booktitle={IEEE Conference on Computer Vision and Pattern Recognition},

  12.   year={2020}

  13. }

  14. ```

  15. 

  16. ## Results and models

  17. 

  18. | PISA | Network | Backbone            | Lr schd | box AP | mask AP | Config | Download |

  19. |:----:|:-------:|:-------------------:|:-------:|:------:|:-------:|:------:|:--------:|

  20. | ×    | Faster R-CNN | R-50-FPN       | 1x      | 36.4   |         | - |

  21. | √    | Faster R-CNN | R-50-FPN       | 1x      | 38.4   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_faster_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_r50_fpn_1x_coco/pisa_faster_rcnn_r50_fpn_1x_coco-dea93523.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_r50_fpn_1x_coco/pisa_faster_rcnn_r50_fpn_1x_coco_20200506_185619.log.json)  |

  22. | ×    | Faster R-CNN | X101-32x4d-FPN | 1x      | 40.1   |         | - |

  23. | √    | Faster R-CNN | X101-32x4d-FPN | 1x      | 41.9   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco-e4accec4.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco/pisa_faster_rcnn_x101_32x4d_fpn_1x_coco_20200505_181503.log.json) |

  24. | ×    | Mask   R-CNN | R-50-FPN       | 1x      | 37.3   | 34.2    | - |

  25. | √    | Mask   R-CNN | R-50-FPN       | 1x      | 39.1   | 35.2    | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_mask_rcnn_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_mask_rcnn_r50_fpn_1x_coco/pisa_mask_rcnn_r50_fpn_1x_coco-dfcedba6.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_mask_rcnn_r50_fpn_1x_coco/pisa_mask_rcnn_r50_fpn_1x_coco_20200508_150500.log.json) |

  26. | ×    | Mask   R-CNN | X101-32x4d-FPN | 1x      | 41.1   | 37.1    | - |

  27. | √    | Mask   R-CNN | X101-32x4d-FPN | 1x      |        |         |   |

  28. | ×    | RetinaNet    | R-50-FPN       | 1x      | 35.6   |         | - |

  29. | √    | RetinaNet    | R-50-FPN       | 1x      | 36.9   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_retinanet_r50_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_r50_fpn_1x_coco/pisa_retinanet_r50_fpn_1x_coco-76409952.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_r50_fpn_1x_coco/pisa_retinanet_r50_fpn_1x_coco_20200504_014311.log.json) |

  30. | ×    | RetinaNet    | X101-32x4d-FPN | 1x      | 39.0   |         | - |

  31. | √    | RetinaNet    | X101-32x4d-FPN | 1x      | 40.7   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco/pisa_retinanet_x101_32x4d_fpn_1x_coco-a0c13c73.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_retinanet_x101_32x4d_fpn_1x_coco/pisa_retinanet_x101_32x4d_fpn_1x_coco_20200505_001404.log.json) |

  32. | ×    | SSD300       | VGG16          | 1x      | 25.6   |         | - |

  33. | √    | SSD300       | VGG16          | 1x      | 27.6   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_ssd300_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd300_coco/pisa_ssd300_coco-710e3ac9.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd300_coco/pisa_ssd300_coco_20200504_144325.log.json) |

  34. | ×    | SSD300       | VGG16          | 1x      | 29.3   |         | - |

  35. | √    | SSD300       | VGG16          | 1x      | 31.8   |         | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/pisa/pisa_ssd512_coco.py) | [model](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco-247addee.pth) &#124; [log](https://download.openmmlab.com/mmdetection/v2.0/pisa/pisa_ssd512_coco/pisa_ssd512_coco_20200508_131030.log.json)  |

  36. 

  37. **Notes:**

  38. 

  39. - In the original paper, all models are trained and tested on mmdet v1.x, thus results may not be exactly the same with this release on v2.0.

  40. - It is noted PISA only modifies the training pipeline so the inference time remains the same with the baseline.

No Description

Contributors (3)
All