- 专利标题: End-to-end saliency mapping via probability distribution prediction
-
申请号: US15138821申请日: 2016-04-26
-
公开(公告)号: US09830529B2公开(公告)日: 2017-11-28
- 发明人: Saumya Jetley , Naila Murray , Eleonora Vig
- 申请人: Xerox Corporation
- 申请人地址: US CT Norwalk
- 专利权人: XEROX CORPORATION
- 当前专利权人: XEROX CORPORATION
- 当前专利权人地址: US CT Norwalk
- 代理机构: Fay Sharpe LLP
- 主分类号: G06K9/00
- IPC分类号: G06K9/00 ; G06E1/00 ; G06K9/46 ; G06K9/62
摘要:
A method for generating a system for predicting saliency in an image and method of use of the prediction system are described. Attention maps for each of a set of training images are used to train the system. The training includes passing the training images though a neural network and optimizing an objective function over the training set which is based on a distance measure computed between a first probability distribution computed for a saliency map output by the neural network and a second probability distribution computed for the attention map for the respective training image. The trained neural network is suited to generation of saliency maps for new images.
公开/授权文献
信息查询