Object Proposal by Multi-Branch Hierarchical Segmentation

Chaoyang Wang, Long Zhao, Shuang Liang, Liqing Zhang, Jinyuan Jia, Yichen Wei

CVPR 2015

doi:10.1109/CVPR.2015.7299012 /cvpr/2015/wang2015cvpr-object/

Abstract

Hierarchical segmentation based object proposal methods have become an important step in modern object detection paradigm. However, standard single-way hierarchical methods are fundamentally flawed in that the errors in early steps cannot be corrected and accumulate. In this work, we propose a novel multi-branch hierarchical segmentation approach that alleviates such problems by learning multiple merging strategies in each step in a complementary manner, such that errors in one merging strategy could be corrected by the others. Our approach achieves the state-of-the-art performance for both object proposal and object detection tasks, comparing to previous object proposal methods.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Object Proposal by Multi-Branch Hierarchical Segmentation." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7299012

Markdown

[Wang et al. "Object Proposal by Multi-Branch Hierarchical Segmentation." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/wang2015cvpr-object/) doi:10.1109/CVPR.2015.7299012

BibTeX

@inproceedings{wang2015cvpr-object,
  title     = {{Object Proposal by Multi-Branch Hierarchical Segmentation}},
  author    = {Wang, Chaoyang and Zhao, Long and Liang, Shuang and Zhang, Liqing and Jia, Jinyuan and Wei, Yichen},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7299012},
  url       = {https://mlanthology.org/cvpr/2015/wang2015cvpr-object/}
}