AttentionNet: Aggregating Weak Directions for Accurate Object Detection
Abstract
We present a novel detection method using a deep convolutional neural network (CNN), named AttentionNet. We cast an object detection problem as an iterative classification problem, which is the most suitable form of a CNN. AttentionNet provides quantized weak directions pointing a target object and the ensemble of iterative predictions from AttentionNet converges to an accurate object boundary box. Since AttentionNet is a unified network for object detection, it detects objects without any separated models from the object proposal to the post bounding-box regression. We evaluate AttentionNet by a human detection task and achieve the state-of-the-art performance of 65% (AP) on PASCAL VOC 2007/2012 with an 8-layered architecture only.
Cite
Text
Yoo et al. "AttentionNet: Aggregating Weak Directions for Accurate Object Detection." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.305Markdown
[Yoo et al. "AttentionNet: Aggregating Weak Directions for Accurate Object Detection." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/yoo2015iccv-attentionnet/) doi:10.1109/ICCV.2015.305BibTeX
@inproceedings{yoo2015iccv-attentionnet,
title = {{AttentionNet: Aggregating Weak Directions for Accurate Object Detection}},
author = {Yoo, Donggeun and Park, Sunggyun and Lee, Joon-Young and Paek, Anthony S. and Kweon, In So},
booktitle = {International Conference on Computer Vision},
year = {2015},
doi = {10.1109/ICCV.2015.305},
url = {https://mlanthology.org/iccv/2015/yoo2015iccv-attentionnet/}
}