Deep salient object detection by integrating multi-level cues

Simple item page
dc.contributor.authorZhang, Jing
dc.contributor.authorDai, Yuchao
dc.contributor.authorPorikli, Fatih
dc.coverage.spatialSanta Rosa, USA
dc.date.accessioned2020-01-19T23:38:30Z
dc.date.createdMarch 24-31 2017
dc.date.issued2017
dc.date.updated2019-11-25T07:22:16Z
dc.description.abstractA key problem in salient object detection is how to effectively exploit the multi-level saliency cues in a unified and data-driven manner. In this paper, building upon the recent success of deep neural networks, we propose a fully convolutional neural network based approach empowered with multi-level fusion to salient object detection. By integrating saliency cues at different levels through fully convolutional neural networks and multi-level fusion, our approach could effectively exploit both learned semantic cues and higher-order region statistics for edge-Accurate salient object detection. First, we fine-Tune a fully convolutional neural network for semantic segmentation to adapt it to salient object detection to learn a suitable yet coarse perpixel saliency prediction map. This map is often smeared across salient object boundaries since the local receptive fields in the convolutional network apply naturally on both sides of such boundaries. Second, to enhance the resolution of the learned saliency prediction and to incorporate higher-order cues that are omitted by the neural network, we propose a multi-level fusion approach where super-pixel level coherency in saliency is exploited. Our extensive experimental results on various benchmark datasets demonstrate that the proposed method outperforms the state-of the-Art approachesen_AU
dc.description.sponsorshipThis work was done when Jing Zhang was a visiting student to the Australian National University/NICTA supported by the China Scholarship Council (No: 201406290108). This work was supported in part by the Australian Research Council grants (DE140100180, DP150104645), and Natural Science Foundation of China grants (61420106007, 61671387).en_AU
dc.format.extent10 pagesen_AU
dc.format.mimetypeapplication/pdfen_AU
dc.identifier.isbn9781509048229en_AU
dc.identifier.urihttp://hdl.handle.net/1885/198501
dc.language.isoen_AUen_AU
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)en_AU
dc.relationhttp://purl.org/au-research/grants/arc/DE140100180en_AU
dc.relationhttp://purl.org/au-research/grants/arc/DP150104645en_AU
dc.relation.ispartofseries17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017
dc.rights© 2017 IEEEen_AU
dc.sourceProceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017en_AU
dc.subjectSemanticsen_AU
dc.subjectObject detectionen_AU
dc.subjectNeural networksen_AU
dc.subjectFeature extractionen_AU
dc.subjectImage segmentationen_AU
dc.subjectImage resolutionen_AU
dc.subjectMachine learningen_AU
dc.titleDeep salient object detection by integrating multi-level cuesen_AU
dc.typeConference paperen_AU
local.contributor.affiliationZhang, Jing, College of Science, The Australian National Universityen_AU
local.contributor.affiliationDai, Yuchao, College of Engineering and Computer Science, The Australian National Universityen_AU
local.contributor.affiliationPorikli, Fatih, College of Engineering and Computer Science, The Australian National Universityen_AU
local.contributor.authoremailrepository.admin@anu.edu.auen_AU
local.contributor.authoruidZhang, Jing, u4066306en_AU
local.contributor.authoruidDai, Yuchao, u4700706en_AU
local.contributor.authoruidPorikli, Fatih, u5405232en_AU
local.description.embargo2037-12-31
local.description.notesImported from ARIESen_AU
local.description.refereedYes
local.identifier.absfor170205 - Neurocognitive Patterns and Neural Networksen_AU
local.identifier.ariespublicationa383154xPUB6176en_AU
local.identifier.doi10.1109/WACV.2017.8en_AU
local.identifier.scopusID2-s2.0-85020214261
local.identifier.uidSubmittedBya383154en_AU
local.publisher.urlhttps://www.ieee.org/en_AU
local.type.statusPublished Versionen_AU

Downloads

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
01 Zhang J et al Deep Salient Object 2017.pdf
Size:
1001.54 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS