February 15, 2020

695 words 4 mins read



CenterMask2 on top of detectron2, in CVPR 2020

repo name youngwanLEE/centermask2
repo link https://github.com/youngwanLEE/centermask2
language Python
size (curr.) 68 kB
stars (curr.) 148
created 2020-02-20
license Apache License 2.0


[CenterMask(original code)][vovnet-detectron2][arxiv] [BibTeX]

CenterMask2 is an upgraded implementation on top of detectron2 beyond original CenterMask based on maskrcnn-benchmark.


  • First anchor-free one-stage instance segmentation. To the best of our knowledge, CenterMask is the first instance segmentation on top of anchor-free object detection (15/11/2019).
  • Toward Real-Time: CenterMask-Lite. This works provide not only large-scale CenterMask but also lightweight CenterMask-Lite that can run at real-time speed (> 30 fps).
  • State-of-the-art performance. CenterMask outperforms Mask R-CNN, TensorMask, and ShapeMask at much faster speed and CenterMask-Lite models also surpass YOLACT or YOLACT++ by large margins.
  • Well balanced (speed/accuracy) backbone network, VoVNetV2. VoVNetV2 shows better performance and faster speed than ResNe(X)t or HRNet.


  • CenterMask2 has been released. (20/02/2020)
  • Lightweight VoVNet has ben released. (26/02/2020)

Results on COCO val


We measure the inference time of all models with batch size 1 on the same V100 GPU machine.

  • pytorch1.3.1
  • CUDA 10.1
  • cuDNN 7.3
  • multi-scale augmentation
  • Unless speficified, no Test-Time Augmentation (TTA)


Method Backbone lr sched inference time mask AP box AP download
Mask R-CNN (detectron2) R-50 3x 0.055 37.2 41.0 model | metrics
Mask R-CNN (detectron2) V2-39 3x 0.052 39.3 43.8 model | metrics
CenterMask (maskrcnn-benchmark) V2-39 3x 0.070 38.5 43.5 link
CenterMask2 V2-39 3x 0.050 39.7 44.2 model | metrics
Mask R-CNN (detectron2) R-101 3x 0.070 38.6 42.9 model | metrics
Mask R-CNN (detectron2) V2-57 3x 0.058 39.7 44.2 model | metrics
CenterMask (maskrcnn-benchmark) V2-57 3x 0.076 39.4 44.6 link
CenterMask2 V2-57 3x 0.058 40.5 45.1 model | metrics
Mask R-CNN (detectron2) X-101 3x 0.129 39.5 44.3 model | metrics
Mask R-CNN (detectron2) V2-99 3x 0.076 40.3 44.9 model | metrics
CenterMask (maskrcnn-benchmark) V2-99 3x 0.106 40.2 45.6 link
CenterMask2 V2-99 3x 0.077 41.4 46.0 model | metrics
CenterMask2 (TTA) V2-99 3x - 42.5 48.6 model | metrics
  • TTA denotes Test-Time Augmentation (multi-scale test).


Method Backbone lr sched inference time mask AP box AP download
YOLACT550 R-50 4x 0.023 28.2 30.3 link
CenterMask (maskrcnn-benchmark) V-19 4x 0.023 32.4 35.9 link
CenterMask2-Lite V-19 4x 0.023 32.8 35.9 model | metrics
YOLACT550 R-101 4x 0.030 28.2 30.3 link
YOLACT550++ R-50 4x 0.029 34.1 - link
YOLACT550++ R-101 4x 0.036 34.6 - link
CenterMask (maskrcnn-benchmark) V-39 4x 0.027 36.3 40.7 link
CenterMask2-Lite V-39 4x 0.028 36.7 40.9 model | metrics
  • Note that The inference time is measured on Titan Xp GPU for fair comparison with YOLACT.

Lightweight VoVNet backbone

Method Backbone Param. lr sched inference time mask AP box AP download
CenterMask2-Lite MobileNetV2 3.5M 4x 0.021 27.2 29.8 model | metrics
CenterMask2-Lite V-19 11.2M 4x 0.023 32.8 35.9 model | metrics
CenterMask2-Lite V-19-Slim 3.1M 4x 0.021 29.8 32.5 model | metrics
CenterMask2-Lite V-19Slim-DW 1.8M 4x 0.020 27.1 29.5 model | metrics
  • DW and Slim denote depthwise separable convolution and a thiner model with half the channel size, respectively.
  • Params. means the number of parameters of backbone.


All you need to use centermask2 is detectron2. It’s easy!
you just install detectron2 following INSTALL.md.
Prepare for coco dataset following this instruction.


ImageNet Pretrained Models

We provide backbone weights pretrained on ImageNet-1k dataset for detectron2.

To train a model, run

cd centermask2
python train_net.py --config-file "configs/<config.yaml>"

For example, to launch CenterMask training with VoVNetV2-39 backbone on 8 GPUs, one should execute:

cd centermask2
python train_net.py --config-file "configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml" --num-gpus 8


Model evaluation can be done similarly:

  • if you want to inference with 1 batch --num-gpus 1
  • --eval-only
  • MODEL.WEIGHTS path/to/the/model.pth
cd centermask2
wget https://dl.dropbox.com/s/tczecsdxt10uai5/centermask2-V-39-eSE-FPN-ms-3x.pth
python train_net.py --config-file "configs/centermask/centermask_V_39_eSE_FPN_ms_3x.yaml" --num-gpus 1 --eval-only MODEL.WEIGHTS centermask2-V-39-eSE-FPN-ms-3x.pth


  • Adding Lightweight models
  • Applying CenterMask for PointRend or Panoptic-FPN.

Citing CenterMask

If you use VoVNet, please use the following BibTeX entry.

  title = {An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection},
  author = {Lee, Youngwan and Hwang, Joong-won and Lee, Sangrok and Bae, Yuseok and Park, Jongyoul},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year = {2019}

  title={CenterMask: Real-Time Anchor-Free Instance Segmentation},
  author={Lee, Youngwan and Park, Jongyoul},

Special Thanks to

mask scoring for detectron2 by Sangrok Lee
FCOS_for_detectron2 by AdeliDet team.

comments powered by Disqus