Awesome

SOTR: Segmenting Objects with Transformers [ICCV 2021]

By Ruohao Guo, Dantong Niu, Liao Qu, Zhenbo Li

Introduction

This is the official implementation of SOTR.

Models

COCO Instance Segmentation Baselines with SOTR

Name	mask AP	AP<sub>50</sub>	AP<sub>75</sub>	AP<sub>S</sub>	AP<sub>M</sub>	AP<sub>L</sub>	download
SOTR_R50	39.6	60.7	42.6	10.3	58.7	72.1	model
SOTR_R101	40.2	61.2	43.4	10.2	59.0	73.1	model
SOTR_R101_DCN	42.0	63.3	45.5	11.4	60.7	74.5	model

Note: The area of APS, APM and APL are calculated by segmentation mask without using bbox information.

Installation & Quick start

First install Detectron2 following the official guide: INSTALL.md.
Then build SOTR with:

https://github.com/easton-cau/SOTR
cd SOTR
python setup.py build develop

Then follow datasets/README.md to set up the datasets (e.g., MS-COCO).

Evaluating

Download the trained models for COCO.

Run the following command

python tools/train_net.py \
    --config-file configs/SOTR/R101.yaml \
    --eval-only \
    --num-gpus 4 \
    MODEL.WEIGHTS work_dir/SOTR_R101/SOTR_R101.pth

Training

Run the following command

python tools/train_net.py \
    --config-file configs/SOTR/R101.yaml \
    --num-gpus 4 \

Acknowledgement

Thanks Detectron2 and AdelaiDet contribution to the community!

The work is supported by National Key R&D Program of China (2020YFD0900204) and Key-Area Research and Development Program of Guangdong Province China (2020B0202010009).

FAQ

If you want to improve the usability or any piece of advice, please feel free to contant directly (ruohguo@foxmail.com).

Citation

Please consider citing our paper in your publications if the project helps your research. BibTeX reference is as follow.

@inproceedings{guo2021sotr,
  title={SOTR: Segmenting Objects with Transformers},
  author={Guo, Ruohao and Niu, Dantong and Qu, Liao and Li, Zhenbo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={7157--7166},
  year={2021}
}