Object Proposal by Multi-Branch Hierarchical Segmentation
Chaoyang Wang, Long Zhao, Shuang Liang, Liqing Zhang, Jinyuan Jia, Yichen Wei
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.
BibTeX
@inproceedings{cvpr2015_objectproposalby,
title = {Object Proposal by Multi-Branch Hierarchical Segmentation},
author = {Chaoyang Wang and Long Zhao and Shuang Liang and Liqing Zhang and Jinyuan Jia and Yichen Wei},
booktitle = {CVPR 2015},
year = {2015}
}