0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

Paper > Integrated Deep and Shallow Networks for Salient Object Detection

Last updated at Posted at 2017-06-06

CNN(ConvNet)関連の論文。

Integrated Deep and Shallow Networks for Salient Object Detection
Jing Zhang, Bo Li, Yuchao Dai, Fatih Porikli, Mingyi He

Cite as:	arXiv:1706.00530 [cs.CV]
 	(or arXiv:1706.00530v1 [cs.CV] for this version)
  • Deep modelでcoarse saliency mapを出力 (1とする)
  • unsupervised saliency mapと(1)をconcatenate
  • Shallow modelで結果を得る

「dipoleの位置情報」と「サイズ」という異なる入力パラメータを分ける場合に使えそうか。

concatenateの詳細は未消化。

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?