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.
@article{arxiv.1506.07704,
title = {AttentionNet: Aggregating Weak Directions for Accurate Object Detection},
author = {Donggeun Yoo and Sunggyun Park and Joon-Young Lee and Anthony S. Paek and In So Kweon},
journal= {arXiv preprint arXiv:1506.07704},
year = {2015}
}