Soft Proposal Networks for Weakly Supervised Object Localization

Yi Zhu Yanzhao Zhou Qixiang Ye Qiang Qiu Jianbin Jiao

Sources

• Files

Arxiv Supp Poster

• Codes

Torch Version PyTorch Version

• Models

SP-GoogLeNet(torch) for ImageNet

Introduction

In this work, we propose a network component called Soft Proposal, which can be inserted after any CNN layer.

The Soft Proposal map iteratively evolves and jointly optimizes with convolutional filters, thus provides objectness information during the end-to-end learning procedure of CNN.

CNN equipped with Soft Proposal can be led to learn better object-centric filters, discover more discriminative visual evidence, and suppress background interference.

Reference

@article{Zhu2017SPN,
  title={{Soft Proposal Networks for Weakly Supervised Object Localization}},
  author={Zhu, Y. and Zhou, Y. and Ye, Q. and Qiu, Q. and Jiao, J.},
  journal={ICCV},
  year={2017}
}