Deep Salience: Visual Salience Modeling via Deep Belief Propagation

Richard Jiang, Danny Crookes

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem’s biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.
Original languageEnglish
Title of host publicationProceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence
PublisherThe AAAI Press
Pages2773-2779
Number of pages7
ISBN (Print)978-1-57735-661-5
Publication statusPublished - Jul 2014
EventThe Twenty-Eighth AAAI Conference on Artificial Intelligence - Quebec City, Canada
Duration: 27 Jul 201431 Jul 2014

Conference

ConferenceThe Twenty-Eighth AAAI Conference on Artificial Intelligence
Country/TerritoryCanada
CityQuebec City
Period27/07/201431/07/2014

Fingerprint

Dive into the research topics of 'Deep Salience: Visual Salience Modeling via Deep Belief Propagation'. Together they form a unique fingerprint.

Cite this