UC-Net: Uncertainty inspired RGB-D saliency detection via conditional variational autoencoders

Jing Zhang, Deng Ping Fan*, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

303 Citations (Scopus)

Abstract

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.

Original languageEnglish
Article number9156838
Pages (from-to)8579-8588
Number of pages10
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Publication statusPublished - 2020
Event2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020 - Virtual, Online, United States
Duration: 14 Jun 202019 Jun 2020

Fingerprint

Dive into the research topics of 'UC-Net: Uncertainty inspired RGB-D saliency detection via conditional variational autoencoders'. Together they form a unique fingerprint.

Cite this