res2net

Res2Net for object detection and instance segmentation

Introduction

[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:

• GFLOPs for classification are calculated with image size (224x224).

@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},
}

Results and Models

Faster R-CNN

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

Mask R-CNN

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

Cascade R-CNN

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

Cascade Mask R-CNN

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

Hybrid Task Cascade (HTC)

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

• Res2Net ImageNet pretrained models are in Res2Net-PretrainedModels.
• More applications of Res2Net are in Res2Net-Github.