FCOS: Fully Convolutional One-Stage Object Detection
Introduction
@article{tian2019fcos,
title={FCOS: Fully Convolutional One-Stage Object Detection},
author={Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},
journal={arXiv preprint arXiv:1904.01355},
year={2019}
}
Results and Models
Backbone |
Style |
GN |
MS train |
Tricks |
DCN |
Lr schd |
Mem (GB) |
Inf time (fps) |
box AP |
Download |
R-50 |
caffe |
N |
N |
N |
N |
1x |
5.2 |
22.9 |
36.2 |
model | log |
R-50 |
caffe |
Y |
N |
N |
N |
1x |
6.5 |
22.7 |
36.6 |
model | log |
R-50 |
caffe |
Y |
N |
Y |
N |
1x |
- |
- |
38.6 |
model | log |
R-50 |
caffe |
Y |
N |
Y |
Y |
1x |
- |
- |
42.5 |
model | log |
R-50 |
caffe |
Y |
N |
N |
N |
2x |
- |
- |
36.9 |
model | log |
R-101 |
caffe |
Y |
N |
N |
N |
1x |
10.2 |
17.3 |
39.2 |
model | log |
R-101 |
caffe |
Y |
N |
N |
N |
2x |
- |
- |
39.1 |
model | log |
Backbone |
Style |
GN |
MS train |
Lr schd |
Mem (GB) |
Inf time (fps) |
box AP |
Download |
R-50 |
caffe |
Y |
Y |
2x |
6.5 |
22.9 |
38.7 |
model | log |
R-101 |
caffe |
Y |
Y |
2x |
10.2 |
17.3 |
40.9 |
model | log |
X-101 |
pytorch |
Y |
Y |
2x |
10.0 |
9.3 |
42.5 |
model | log |
Notes:
- To be consistent with the author's implementation, we use 4 GPUs with 4 images/GPU for R-50 and R-101 models, and 8 GPUs with 2 image/GPU for X-101 models.
- The X-101 backbone is X-101-64x4d.
- Tricks means setting
norm_on_bbox
, centerness_on_reg
, center_sampling
as True
.
- DCN means using
DCNv2
in both backbone and head.