AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 233
  • Download : 413
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.
Publisher
IEEE Computer Society and the Computer Vision Foundation (CVF)
Issue Date
2015-12-15
Language
English
Citation

IEEE International Conference on Computer Vision (ICCV 2015)

URI
http://hdl.handle.net/10203/204133
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
1506.07704.pdf(2.12 MB)Download

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0