Skip to content

Latest commit

 

History

History
50 lines (39 loc) · 1.69 KB

README.md

File metadata and controls

50 lines (39 loc) · 1.69 KB
Raw

Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism

this is the source code of our work GRM-Net. In this work, we solve the problem of Multi-instance referring segmentation in Sketch Scenes.

Requirements

  • Linux or macOS with Python ≥ 3.6
  • PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this
  • OpenCV is optional and needed by demo and visualization

Steps

  1. Install and build libs
git clone https://github.com/PeizeSun/SparseR-CNN.git
cd SparseR-CNN
python setup.py build develop
  1. Train GRM-Net
python projects/MRCNN/train_net.py --num-gpus 1 \
    --config-file projects/MRCNN/configs/maskrcnn_r_101_3x.yaml
  1. Evaluate GRM-Net
python projects/MRCNN/train_net.py --num-gpus 1 \
    --config-file projects/MRCNN/configs/maskrcnn_r_101_3x.yaml \
    --eval-only MODEL.WEIGHTS path/to/model.pth

Citing

If you use GRM-Net in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@inproceedings {10.2312:pg.20221238,
booktitle = {Pacific Graphics Short Papers, Posters, and Work-in-Progress Papers},
editor = {Yang, Yin and Parakkat, Amal D. and Deng, Bailin and Noh, Seung-Tak},
title = {{Multi-instance Referring Image Segmentation of Scene Sketches based on Global Reference Mechanism}},
author = {Ling, Peng and Mo, Haoran and Gao, Chengying},
year = {2022},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-190-8},
DOI = {10.2312/pg.20221238}
}