Chained Cascade Network for Object Detection
Abstract
Cascade is a widely used approach that rejects obvious negative samples at early stages for learning better classifier and faster inference. This paper presents chained cascade network (CC-Net). In this CC-Net, there are many cascade stages. Preceding cascade stages are placed at shallow layers. Easy hard examples are rejected at shallow layers so that the computation for deeper or wider layers is not required. In this way, features and classifiers at latter stages handle more difficult samples with the help of features and classifiers in previous stages. It yields consistent boost in detection performance on PASCAL VOC 2007 and ImageNet for both fast RCNN and Faster RCNN. CC-Net saves computation for both training and testing. Code is available on.
Cite
Text
Ouyang et al. "Chained Cascade Network for Object Detection." International Conference on Computer Vision, 2017. doi:10.1109/ICCV.2017.214Markdown
[Ouyang et al. "Chained Cascade Network for Object Detection." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/ouyang2017iccv-chained/) doi:10.1109/ICCV.2017.214BibTeX
@inproceedings{ouyang2017iccv-chained,
title = {{Chained Cascade Network for Object Detection}},
author = {Ouyang, Wanli and Wang, Kun and Zhu, Xin and Wang, Xiaogang},
booktitle = {International Conference on Computer Vision},
year = {2017},
doi = {10.1109/ICCV.2017.214},
url = {https://mlanthology.org/iccv/2017/ouyang2017iccv-chained/}
}