UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the saliency detection task as a point estimation problem, and produce a single saliency map following...

Full description

Bibliographic Details

Published in:	Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 8579 - 8588
Main Authors:	Zhang, Jing, Fan, Deng-Ping, Dai, Yuchao, Anwar, Saeed, Saleh, Fatemeh Sadat, Zhang, Tong, Barnes, Nick
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.01.2020
Subjects:	Labeling Pipelines Predictive models Probabilistic logic Saliency detection Training Uncertainty
ISSN:	1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!