Cross-Domain Weakly-Supervised Object Detection & GUI Application

https://github.com/ranran4082391/corss-domain

 

Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation

This page is for the paper appeared in CVPR2018. You can also find project page for the paper.

Here is the example of our results in watercolor images.

 

Cross-Domain Weakly-Supervised Object Detection & GUI Application_第1张图片

 

 

Requirements

  • Python 3.5+
  • Chainer 3.0+
  • ChainerCV 0.8
  • Cupy 2.0+
  • OpenCV 3+
  • Matplotlib

Please install all the libraries. We recommend pip install -r requirements.txt.

GUI Application

Aiming at the CVPR paper in 2018, the model transplantation is realized. By designing GUI reference program, the user can intuitively feel the image instantiation labeling by weak labels, which greatly reduces the workload of image instantiation labeling.

Execute GUI.py

你可能感兴趣的