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

Saved in:
Bibliographic Details
Main Authors: Zhang, Jing, Fan, Deng-Ping, Dai, Yuchao, Anwar, Saeed, Saleh, Fatemeh Sadat, Zhang, Tong, Barnes, Nick
Format: Conference Proceeding
Language:English
Subjects:
Labeling
Pipelines
Predictive models
Probabilistic logic
Saliency detection
Training
Uncertainty
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 a deterministic learning pipeline. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the latent space. With the proposed saliency consensus process, we are able to generate an accurate saliency map based on these multiple predictions. Quantitative and qualitative evaluations on six challenging benchmark datasets against 18 competing algorithms demonstrate the effectiveness of our approach in learning the distribution of saliency maps, leading to a new state-of-the-art in RGB-D saliency detection.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.00861