HFS: Hierarchical Feature Selection for Efficient Image Segmentation
Abstract
In this paper, we propose a real-time system, Hierarchical Feature Selection (HFS), that performs image segmentation at a speed of 50 frames-per-second. We make an attempt to improve the performance of previous image segmentation systems by focusing on two aspects: (1) a careful system implementation on modern GPUs for efficient feature computation; and (2) an effective hierarchical feature selection and fusion strategy with learning. Compared with classic segmentation algorithms, our system demonstrates its particular advantage in speed, with comparable results in segmentation quality. Adopting HFS in applications like salient object detection and object proposal generation results in a significant performance boost. Our proposed HFS system (will be open-sourced) can be used in a variety computer vision tasks that are built on top of image segmentation and superpixel extraction.
Cite
Text
Cheng et al. "HFS: Hierarchical Feature Selection for Efficient Image Segmentation." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46487-9_53Markdown
[Cheng et al. "HFS: Hierarchical Feature Selection for Efficient Image Segmentation." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/cheng2016eccv-hfs/) doi:10.1007/978-3-319-46487-9_53BibTeX
@inproceedings{cheng2016eccv-hfs,
title = {{HFS: Hierarchical Feature Selection for Efficient Image Segmentation}},
author = {Cheng, Ming-Ming and Liu, Yun and Hou, Qibin and Bian, Jiawang and Torr, Philip H. S. and Hu, Shi-Min and Tu, Zhuowen},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {867-882},
doi = {10.1007/978-3-319-46487-9_53},
url = {https://mlanthology.org/eccv/2016/cheng2016eccv-hfs/}
}