by Zhaowei Cai and Nuno Vasconcelos
This repository is written by Zhaowei Cai at UC San Diego, on the base of Detectron @ e8942c8.
This repository re-implements Cascade R-CNN on the base of Detectron. Very consistent gains are available for all tested models, regardless of baseline strength.
Please follow Detectron on how to install and use Detectron-Cascade-RCNN.
It is also recommended to use our original implementation, cascade-rcnn based on Caffe, and the third-party implementation, mmdetection based on PyTorch and tensorpack based on TensorFlow.
If you use our code/model/data, please cite our paper:
@inproceedings{cai18cascadercnn,
author = {Zhaowei Cai and Nuno Vasconcelos},
Title = {Cascade R-CNN: Delving into High Quality Object Detection},
booktitle = {CVPR},
Year = {2018}
}
or its extension:
@article{cai2019cascadercnn,
author = {Zhaowei Cai and Nuno Vasconcelos},
title = {Cascade R-CNN: High Quality Object Detection and Instance Segmentation},
journal = {arXiv preprint arXiv:1906.09756},
year = {2019}
}
and Detectron:
@misc{Detectron2018,
author = {Ross Girshick and Ilija Radosavovic and Georgia Gkioxari and
Piotr Doll\'{a}r and Kaiming He},
title = {Detectron},
howpublished = {\url{https://github.com/facebookresearch/detectron}},
year = {2018}
}
| backbone | type | lr schd |
im/ gpu |
box AP |
box AP50 |
box AP75 |
mask AP |
mask AP50 |
mask AP75 |
download links |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN-baseline | Faster | 1x | 2 | 36.7 | 58.4 | 39.6 | - | - | - | model | boxes |
| R-50-FPN-cascade | Faster | 1x | 2 | 40.9 | 59.0 | 44.6 | - | - | - | model | boxes |
| R-101-FPN-baseline | Faster | 1x | 2 | 39.4 | 61.2 | 43.4 | - | - | - | model | boxes |
| R-101-FPN-cascade | Faster | 1x | 2 | 42.8 | 61.4 | 46.1 | - | - | - | model | boxes |
| X-101-64x4d-FPN-baseline | Faster | 1x | 1 | 41.5 | 63.8 | 44.9 | - | - | - | model | boxes |
| X-101-64x4d-FPN-cascade | Faster | 1x | 1 | 45.4 | 64.0 | 49.8 | - | - | - | model | boxes |
| X-101-32x8d-FPN-baseline | Faster | 1x | 1 | 41.3 | 63.7 | 44.7 | - | - | - | model | boxes |
| X-101-32x8d-FPN-cascade | Faster | 1x | 1 | 44.7 | 63.7 | 48.8 | - | - | - | model | boxes |
| R-50-FPN-baseline | Mask | 1x | 2 | 37.7 | 59.2 | 40.9 | 33.9 | 55.8 | 35.8 | model | boxes | masks |
| R-50-FPN-cascade | Mask | 1x | 2 | 41.3 | 59.6 | 44.9 | 35.4 | 56.2 | 37.8 | model | boxes | masks |
| R-101-FPN-baseline | Mask | 1x | 2 | 40.0 | 61.8 | 43.7 | 35.9 | 58.3 | 38.0 | model | boxes | masks |
| R-101-FPN-cascade | Mask | 1x | 2 | 43.3 | 61.7 | 47.2 | 37.1 | 58.6 | 39.8 | model | boxes | masks |
| X-101-64x4d-FPN-baseline | Mask | 1x | 1 | 42.4 | 64.3 | 46.4 | 37.5 | 60.6 | 39.9 | model | boxes | masks |
| X-101-64x4d-FPN-cascade | Mask | 1x | 1 | 45.9 | 64.4 | 50.2 | 38.8 | 61.3 | 41.6 | model | boxes | masks |
| X-101-32x8d-FPN-baseline | Mask | 1x | 1 | 42.1 | 64.1 | 45.9 | 37.3 | 60.3 | 39.5 | model | boxes | masks |
| X-101-32x8d-FPN-cascade | Mask | 1x | 1 | 45.8 | 64.1 | 50.3 | 38.6 | 60.6 | 41.5 | model | boxes | masks |
| backbone | type | lr schd |
im/ gpu |
box AP |
box AP50 |
box AP75 |
mask AP |
mask AP50 |
mask AP75 |
download links |
|---|---|---|---|---|---|---|---|---|---|---|
| X-152-32x8d-FPN-IN5k-baseline | Mask | s1x | 1 | 48.1 | 68.3 | 52.9 | 41.5 | 65.1 | 44.7 | model | boxes | masks |
| [above without test-time aug.] | 45.2 | 66.9 | 49.7 | 39.7 | 63.5 | 42.4 | ||||
| X-152-32x8d-FPN-IN5k-cascade | Mask | s1x | 1 | 50.2 | 68.2 | 55.0 | 42.3 | 65.4 | 45.8 | model | boxes | masks |
| [above without test-time aug.] | 48.1 | 66.7 | 52.6 | 40.7 | 63.7 | 43.8 |
| backbone | type | lr schd |
im/ gpu |
box AP |
box AP50 |
box AP75 |
mask AP |
mask AP50 |
mask AP75 |
download links |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN-GN-baseline | Faster | 1x | 2 | 38.4 | 59.9 | 41.7 | - | - | - | model | boxes |
| R-50-FPN-GN-cascade | Faster | 1x | 2 | 42.2 | 60.6 | 45.8 | - | - | - | model | boxes |
| R-101-FPN-GN-baseline | Faster | 1x | 2 | 39.9 | 61.3 | 43.3 | - | - | - | model | boxes |
| R-101-FPN-GN-cascade | Faster | 1x | 1 | 43.8 | 62.2 | 47.6 | - | - | - | model | boxes |
| R-50-FPN-GN-baseline | Mask | 1x | 2 | 39.2 | 60.5 | 42.9 | 34.9 | 57.1 | 36.9 | model | boxes |
| R-50-FPN-GN-cascade | Mask | 1x | 1 | 42.9 | 60.7 | 46.6 | 36.6 | 57.7 | 39.2 | model | boxes | masks |
| R-101-FPN-GN-baseline | Mask | 1x | 2 | 41.1 | 62.1 | 45.1 | 36.3 | 58.9 | 38.5 | model | boxes | masks |
| R-101-FPN-GN-cascade | Mask | 1x | 1 | 44.8 | 62.8 | 48.8 | 38.0 | 59.8 | 40.8 | model | boxes | masks |
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent