Architecture | Softmax, RPN, Convolution, Dense Connections, FPN, Res2Net, RoIAlign |
---|---|
lr sched | 20e |
SHOW MORE |
Architecture | RPN, Convolution, FPN, Res2Net, 1x1 Convolution, HTC, RoIAlign |
---|---|
lr sched | 20e |
SHOW MORE |
Architecture | Softmax, RPN, Convolution, Dense Connections, FPN, Res2Net, RoIAlign |
---|---|
lr sched | 2x |
SHOW MORE |
[ALGORITHM]
We propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.
Backbone | Params. | GFLOPs | top-1 err. | top-5 err. |
---|---|---|---|---|
ResNet-101 | 44.6 M | 7.8 | 22.63 | 6.44 |
ResNeXt-101-64x4d | 83.5M | 15.5 | 20.40 | - |
HRNetV2p-W48 | 77.5M | 16.1 | 20.70 | 5.50 |
Res2Net-101 | 45.2M | 8.3 | 18.77 | 4.64 |
Compared with other backbone networks, Res2Net requires fewer parameters and FLOPs.
Note:
@article{gao2019res2net,
title={Res2Net: A New Multi-scale Backbone Architecture},
author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
journal={IEEE TPAMI},
year={2020},
doi={10.1109/TPAMI.2019.2938758},
}
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
---|---|---|---|---|---|---|---|
R2-101-FPN | pytorch | 2x | 7.4 | - | 43.0 | config | model | log |
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
---|---|---|---|---|---|---|---|---|
R2-101-FPN | pytorch | 2x | 7.9 | - | 43.6 | 38.7 | config | model | log |
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | Config | Download |
---|---|---|---|---|---|---|---|
R2-101-FPN | pytorch | 20e | 7.8 | - | 45.7 | config | model | log |
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
---|---|---|---|---|---|---|---|---|
R2-101-FPN | pytorch | 20e | 9.5 | - | 46.4 | 40.0 | config | model | log |
Backbone | Style | Lr schd | Mem (GB) | Inf time (fps) | box AP | mask AP | Config | Download |
---|---|---|---|---|---|---|---|---|
R2-101-FPN | pytorch | 20e | - | - | 47.5 | 41.6 | config | model | log |
MODEL | BOX AP |
---|---|
HTC (R2-101-FPN, 20e, pytorch) | 47.5 |
Cascade Mask R-CNN (R2-101-FPN, 20e, pytorch) | 46.4 |
Cascade R-CNN (R2-101-FPN, 20e, pytorch) | 45.7 |
Mask R-CNN (R2-101-FPN, 2x, pytorch) | 43.6 |
Faster R-CNN (R2-101-FPN, 2x, pytorch) | 43.0 |
MODEL | MASK AP |
---|---|
HTC (R2-101-FPN, 20e, pytorch) | 41.6 |
Cascade Mask R-CNN (R2-101-FPN, 20e, pytorch) | 40.0 |
Mask R-CNN (R2-101-FPN, 2x, pytorch) | 38.7 |