Home

Awesome

Res2Net for object detection and instance segmentation based on mmdetection.

News

Introduction

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.

BackboneParams.GFLOPstop-1 err.top-5 err.
ResNet-10144.6 M7.822.636.44
ResNeXt-101-64x4d83.5M15.520.40-
HRNetV2p-W4877.5M16.120.705.50
Res2Net-10145.2M8.318.774.64

Compared with other backbone networks, Res2Net requires fewer parameters and FLOPs.

Note:

Detection and segmentation Results

Faster R-CNN

BackboneParams.GFLOPsbox AP
R-101-FPN60.52M283.1439.4
X-101-64x4d-FPN99.25M440.3641.3
HRNetV2p-W4883.36M459.6641.5
Res2Net-10161.18M293.6842.3

Mask R-CNN

BackboneParams.GFLOPsbox APmask AP
R-101-FPN63.17M351.6540.336.5
X-101-64x4d-FPN101.9M508.8742.037.7
HRNetV2p-W4886.01M528.1742.938.3
Res2Net-10163.83M362.1843.338.6

Cascade R-CNN

BackboneParams.GFLOPsbox AP
R-101-FPN88.16M310.7842.5
X-101-64x4d-FPN126.89M468.0044.7
HRNetV2p-W48111.00M487.3044.6
Res2Net-10188.82M321.3245.5

Cascade Mask R-CNN

BackboneParams.GFLOPsbox APmask AP
R-101-FPN96.09M516.3043.337.6
X-101-64x4d-FPN134.82M673.5245.739.4
HRNetV2p-W48118.93M692.8246.039.5
Res2Net-10196.75M526.8446.139.4

Hybrid Task Cascade (HTC)

BackboneParams.GFLOPsbox APmask AP
R-101-FPN99.03M563.7644.939.4
X-101-64x4d-FPN137.75M720.9846.940.8
HRNetV2p-W48121.87M740.2847.041.0
Res2Net-10199.69M574.3047.541.3

Note:

MMDetection

News: We released the technical report on ArXiv.

Documentation: https://mmdetection.readthedocs.io/

Introduction

The master branch works with PyTorch 1.1 to 1.4.

mmdetection is an open source object detection toolbox based on PyTorch. It is a part of the open-mmlab project developed by Multimedia Laboratory, CUHK.

demo image

Major features

Apart from MMDetection, we also released a library mmcv for computer vision research, which is heavily depended on by this toolbox.

License

This project is released under the Apache 2.0 license.

Changelog

v1.1.0 was released in 24/2/2020. Please refer to CHANGELOG.md for details and release history.

Benchmark and model zoo

Supported methods and backbones are shown in the below table. Results and models are available in the Model zoo.

ResNetResNeXtSENetVGGHRNetRes2Net
RPN
Fast R-CNN
Faster R-CNN
Mask R-CNN
Cascade R-CNN
Cascade Mask R-CNN
SSD
RetinaNet
GHM
Mask Scoring R-CNN
Double-Head R-CNN
Grid R-CNN (Plus)
Hybrid Task Cascade
Libra R-CNN
Guided Anchoring
FCOS
RepPoints
Foveabox
FreeAnchor
NAS-FPN
ATSS

Other features

Installation

Please refer to INSTALL.md for installation and dataset preparation.

Get Started

Please see GETTING_STARTED.md for the basic usage of MMDetection.

Contributing

We appreciate all contributions to improve MMDetection. Please refer to CONTRIBUTING.md for the contributing guideline.

Acknowledgement

MMDetection is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new detectors.

Citation

If you use this toolbox or benchmark in your research, please cite this project.

@article{mmdetection,
  title   = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
  author  = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
             Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
             Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
             Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
             Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
             and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
  journal= {arXiv preprint arXiv:1906.07155},
  year={2019}
}

Contact

This repo is currently maintained by Kai Chen (@hellock), Yuhang Cao (@yhcao6), Wenwei Zhang (@ZwwWayne), Jiarui Xu (@xvjiarui). Other core developers include Jiangmiao Pang (@OceanPang) and Jiaqi Wang (@myownskyW7).