Uncertainty Inspired RGB-D Saliency Detection

We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipel...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-09, Vol.44 (9), p.5761-5779
Main Authors: Zhang, Jing, Fan, Deng-Ping, Dai, Yuchao, Anwar, Saeed, Saleh, Fatemeh, Aliakbarian, Sadegh, Barnes, Nick
Format: Article
Language:English
Subjects:
alternating back-propagation
Back propagation
Coders
conditional variational autoencoders
Data models
Encoders-Decoders
Labeling
Labelling
Learning
Pipelines
Predictive models
RGB-D saliency detection
Salience
Saliency detection
Source code
Training
Uncertainty
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet .
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2021.3073564