Deep salient object detection by integrating multi-level cues
dc.contributor.author | Zhang, Jing | |
dc.contributor.author | Dai, Yuchao | |
dc.contributor.author | Porikli, Fatih | |
dc.coverage.spatial | Santa Rosa, USA | |
dc.date.accessioned | 2020-01-19T23:38:30Z | |
dc.date.created | March 24-31 2017 | |
dc.date.issued | 2017 | |
dc.date.updated | 2019-11-25T07:22:16Z | |
dc.description.abstract | A 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 approaches | en_AU |
dc.description.sponsorship | This 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.extent | 10 pages | en_AU |
dc.format.mimetype | application/pdf | en_AU |
dc.identifier.isbn | 9781509048229 | en_AU |
dc.identifier.uri | http://hdl.handle.net/1885/198501 | |
dc.language.iso | en_AU | en_AU |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | en_AU |
dc.relation | http://purl.org/au-research/grants/arc/DE140100180 | en_AU |
dc.relation | http://purl.org/au-research/grants/arc/DP150104645 | en_AU |
dc.relation.ispartofseries | 17th IEEE Winter Conference on Applications of Computer Vision, WACV 2017 | |
dc.rights | © 2017 IEEE | en_AU |
dc.source | Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017 | en_AU |
dc.subject | Semantics | en_AU |
dc.subject | Object detection | en_AU |
dc.subject | Neural networks | en_AU |
dc.subject | Feature extraction | en_AU |
dc.subject | Image segmentation | en_AU |
dc.subject | Image resolution | en_AU |
dc.subject | Machine learning | en_AU |
dc.title | Deep salient object detection by integrating multi-level cues | en_AU |
dc.type | Conference paper | en_AU |
local.contributor.affiliation | Zhang, Jing, College of Science, The Australian National University | en_AU |
local.contributor.affiliation | Dai, Yuchao, College of Engineering and Computer Science, The Australian National University | en_AU |
local.contributor.affiliation | Porikli, Fatih, College of Engineering and Computer Science, The Australian National University | en_AU |
local.contributor.authoremail | repository.admin@anu.edu.au | en_AU |
local.contributor.authoruid | Zhang, Jing, u4066306 | en_AU |
local.contributor.authoruid | Dai, Yuchao, u4700706 | en_AU |
local.contributor.authoruid | Porikli, Fatih, u5405232 | en_AU |
local.description.embargo | 2037-12-31 | |
local.description.notes | Imported from ARIES | en_AU |
local.description.refereed | Yes | |
local.identifier.absfor | 170205 - Neurocognitive Patterns and Neural Networks | en_AU |
local.identifier.ariespublication | a383154xPUB6176 | en_AU |
local.identifier.doi | 10.1109/WACV.2017.8 | en_AU |
local.identifier.scopusID | 2-s2.0-85020214261 | |
local.identifier.uidSubmittedBy | a383154 | en_AU |
local.publisher.url | https://www.ieee.org/ | en_AU |
local.type.status | Published Version | en_AU |
Downloads
Original bundle
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: