- Patent Title: End-to-end saliency mapping via probability distribution prediction
-
Application No.: US15138821Application Date: 2016-04-26
-
Publication No.: US09830529B2Publication Date: 2017-11-28
- Inventor: Saumya Jetley , Naila Murray , Eleonora Vig
- Applicant: Xerox Corporation
- Applicant Address: US CT Norwalk
- Assignee: XEROX CORPORATION
- Current Assignee: XEROX CORPORATION
- Current Assignee Address: US CT Norwalk
- Agency: Fay Sharpe LLP
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06E1/00 ; G06K9/46 ; G06K9/62

Abstract:
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.
Public/Granted literature
- US20170308770A1 END-TO-END SALIENCY MAPPING VIA PROBABILITY DISTRIBUTION PREDICTION Public/Granted day:2017-10-26
Information query