tbergman / Object-Detection-for-Graphical-User-Interface

Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?

Accepted to ESEC/FSE2020

This repository includes all code/pretrained models in our paper, namely Faster RCNN, YOLO v3, CenterNet, Xianyu, REMAUI and our model

RESOURCE

CODE

All code is tested under Ubuntu 16.04, Cuda 9.0, PyThon 3.9, torch 1.12.1, Nvidia 1080 Ti

FasterRNN is also tested under Ubuntu 22.04, Cuda 12.0, Python 3.10, pytorch 2.2.0, Nvidia 1080 Ti. Please refer to DL_setup_troubleshootiing.md to see how to adjust the cu files.

Our model

See GitHub

Baselines

See the corresponding folder in this repository. Each folder contains an individual README file.

Faster RCNN, YOLOv3, CenterNet, Xianyu

For REAMUI, see pix2app

ACKNOWNLEDGES

The implementations of Faster RCNN, YOLO v3, CenterNet and REMAUI are based on the following GitHub Repositories. Thank for the works.

We implement Xianyu based on their technical blog

COCOApi: https://github.com/cocodataset/cocoapi

Citation

@inproceedings{chen2020object,
  title={Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?},
  author={Chen, Jieshan and Xie, Mulong and Xing, Zhenchang and Chen, Chunyang and Xu, Xiwei, Zhu, Liming and Guoqiang Li},
  booktitle={Proceedings of the 2020 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering},
  year={2020},
  publisher = "ACM",
  address = "New York, NY",
  doi = "10.1145/3368089.3409691",
}

@inbook{UIED,
  author = {Xie, Mulong and Feng, Sidong and Xing, Zhenchang and Chen, Jieshan and Chen, Chunyang},
  title = {UIED: A Hybrid Tool for GUI Element Detection},
  year = {2020},
  isbn = {9781450370431},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3368089.3417940},
  booktitle = {Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering},
  pages = {1655–1659},
  numpages = {5}
}

About

Object Detection for Graphical User Interface: Old Fashioned or Deep Learning or a Combination?

License:Apache License 2.0


Languages

Language:Python 80.1%Language:Cuda 8.9%Language:C 5.1%Language:Cython 2.4%Language:C++ 2.3%Language:Shell 1.0%Language:MATLAB 0.2%