Object Proposal by Multi-Branch Hierarchical Segmentation

Chaoyang Wang, Long Zhao, Shuang Liang, Liqing Zhang, Jinyuan Jia, Yichen Wei; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3873-3881

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Wang_2015_CVPR,
author = {Wang, Chaoyang and Zhao, Long and Liang, Shuang and Zhang, Liqing and Jia, Jinyuan and Wei, Yichen},
title = {Object Proposal by Multi-Branch Hierarchical Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}