AttentionNet: AggregatingWeak Directions for Accurate Object Detection

作者:Yoo Donggeun*; Park Sunggyun; Lee Joon Young; Paek Anthony S; Kweon In So
来源:IEEE International Conference on Computer Vision, 2015-12-11 To 2015-12-18.
DOI:10.1109/ICCV.2015.305

摘要

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.

  • 出版日期2015