ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation

by Di Lin, Dingguo Shen, Siting Shen,Yuanfeng Ji,Dani Lischinski,Daniel Cohen-Or,Hui Huang

Introduction

This repository re-implements ZigZagNet on the base of Detectron. Very consistent gains are available for all tested models, regardless of baseline strength.

Please follow Detectron on how to install and use ZigZagNet.

Citation

If you use our code/model/data, please cite our paper:

@inproceedings{cai18cascadercnn,
  author = {Di Lin, Dingguo Shen, Siting Shen,Yuanfeng Ji,Dani Lischinski,Daniel Cohen-Or,Hui Huang},
  Title = {ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation},
  booktitle = {CVPR},
  Year  = {2019}
}

and Detectron:

@misc{Detectron2018,
  author =       {Ross Girshick and Ilija Radosavovic and Georgia Gkioxari and
                  Piotr Doll'{a}r and Kaiming He},
  title =        {Detectron},
  howpublished = {url{https://github.com/facebookresearch/detectron}},
  year =         {2018}
}

Benchmarking

End-to-End Mask R-CNN Baselines

All models were tested on the coco_2017_val dataset

Model

The model weights that can reproduce numbers in our paper will be coming soon.