English

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Computer Vision and Pattern Recognition 2015-09-29 v2 Machine Learning

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.

Keywords

Cite

@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}
}

Comments

To appear in ICCV 2015

R2 v1 2026-06-22T10:00:05.611Z