Learning to Count with CNN Boosting
Abstract
In this paper, we address the task of object counting in images. We follow modern learning approaches in which a density map is estimated directly from the input image. We employ CNNs and incorporate two significant improvements to the state of the art methods: layered boosting and selective sampling. As a result, we manage both to increase the counting accuracy and to reduce processing time. Moreover, we show that the proposed method is effective, even in the presence of labeling errors. Extensive experiments on five different datasets demonstrate the efficacy and robustness of our approach. Mean Absolute error was reduced by 20 % to 35 %. At the same time, the training time of each CNN has been reduced by 50 %.
Cite
Text
Walach and Wolf. "Learning to Count with CNN Boosting." European Conference on Computer Vision, 2016. doi:10.1007/978-3-319-46475-6_41Markdown
[Walach and Wolf. "Learning to Count with CNN Boosting." European Conference on Computer Vision, 2016.](https://mlanthology.org/eccv/2016/walach2016eccv-learning/) doi:10.1007/978-3-319-46475-6_41BibTeX
@inproceedings{walach2016eccv-learning,
title = {{Learning to Count with CNN Boosting}},
author = {Walach, Elad and Wolf, Lior},
booktitle = {European Conference on Computer Vision},
year = {2016},
pages = {660-676},
doi = {10.1007/978-3-319-46475-6_41},
url = {https://mlanthology.org/eccv/2016/walach2016eccv-learning/}
}