Skip to content
Branch: master
Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
..
Failed to load latest commit information.
data/demo
datasets
experiments
external
fetch_data
functions
imdb
init
models
utils
.gitattributes
.gitignore
LICENSE
README.md
dual_build.m
startup.m

README.md

A Dual-Network Progressive Approach to Weakly Supervised Object Detection

By Xuanyi Dong, Deyu Meng, Fan Ma, Yi Yang. This paper is accepted by ACM Multimedia 2017.

Introduction

Dual-Network is a weakly supervised object detection framework leveraging deep CNN models.

This project is modified on the Matlab code of R-FCN and Fast R-CNN.

License

Dual-Network is released under the MIT License (refer to the LICENSE file for details).

Resources & Preparation

  1. ImageNet-pretrained networks: Google Drive. Please save the models into the corresponding sub-directory of models/pre_trained_models.
  2. The initial pseudo labels for PASCAL VOC 2007 by ContextLocNet : Google Drive. Please save and extract it into data.
  3. The pre-computed region proposals: Google Drive. Please save and extract it into data.
  4. Download the PASCAL VOC 2007 data into datasets, following the README in datasets.
  5. Compile Caffe located in external/caffe.
  6. Run dual_build.m to complie the nms mex functions.
  7. Run startup.m to add necessary paths.

Training & Testing

  • [TODO] re-organize the experiment codes.

Citing Dual-Network

If you find Dual-Network useful in your research, please consider citing:

@inproceedings{dong2017dual,
    title={A Dual-Network Progressive Approach to Weakly Supervised Object Detection},
    author={Dong, Xuanyi and Meng, Deyu and Ma, Fan and Yang, Yi},
    booktitle={Proceedings of the 2017 ACM on Multimedia Conference},
    pages={279--287},
    year={2017},
    organization={ACM}
}
@inproceedings{kantorov2016,
    title = {ContextLocNet: Context-aware Deep Network Models for Weakly Supervised Localization},
    author = {Kantorov, V., Oquab, M., Cho M. and Laptev, I.},
    booktitle = {Proc. European Conference on Computer Vision (ECCV), 2016},
    year = {2016}
}
@article{dai16rfcn,
    Author = {Jifeng Dai, Yi Li, Kaiming He, Jian Sun},
    Title = {{R-FCN}: Object Detection via Region-based Fully Convolutional Networks},
    Journal = {arXiv preprint arXiv:1605.06409},
    Year = {2016}
}
@inproceedings{girshick2015fast,
    title={Fast R-CNN},
    author={Girshick, Ross},
    booktitle={Proceedings of the IEEE international conference on computer vision},
    pages={1440--1448},
    year={2015}
}
You can’t perform that action at this time.