Saliency ranking using deep learning
| dc.contributor.author | Kalash, Mahmoud | |
| dc.contributor.examiningcommittee | Wang, Yang (Computer Science) | en_US |
| dc.contributor.examiningcommittee | Jozani, Mohammad Jafari (Department of Statistics) | en_US |
| dc.contributor.supervisor | Bruce, Neil (Computer Science) | en_US |
| dc.date.accessioned | 2018-09-14T14:51:16Z | |
| dc.date.available | 2018-09-14T14:51:16Z | |
| dc.date.issued | 2018 | en_US |
| dc.date.submitted | 2018-07-09T17:31:47Z | en |
| dc.degree.discipline | Computer Science | en_US |
| dc.degree.level | Master of Science (M.Sc.) | en_US |
| dc.description.abstract | Salient object detection is a problem that has been considered in detail and many solutions proposed. In this thesis, we argue that work to date has addressed a problem that is relatively ill-posed. Specifically, there is not universal agreement about what constitutes a salient object when multiple observers are queried which implies a relative rank exists on salient objects. In this thesis, we solve this more general problem that considers relative rank. A novel deep learning solution is proposed based on a hierarchical representation of relative saliency and stage-wise refinement to address both of the saliency ranking and subitizing tasks. We also present methods for deriving suitable ranked salient object instances to generate a large scale dataset for saliency ranking, along with metrics suitable to measuring success in a relative object saliency landscape. Our approach exceeds performance of any prior work across all metrics considered (both traditional and newly proposed). | en_US |
| dc.description.note | October 2018 | en_US |
| dc.identifier.citation | M. A. Islam*, M. Kalash* and N. Bruce. "Revisiting Salient Object Detection: Simultaneous Detection, Ranking, and Subitizing of Multiple Salient Objects." 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA. IEEE, June 2018. | en_US |
| dc.identifier.uri | http://hdl.handle.net/1993/33368 | |
| dc.language.iso | eng | en_US |
| dc.rights | open access | en_US |
| dc.subject | Deep Learning | en_US |
| dc.subject | Convolutional Neural Networks | en_US |
| dc.subject | Saliency Detection | en_US |
| dc.subject | Saliency Ranking | en_US |
| dc.title | Saliency ranking using deep learning | en_US |
| dc.type | master thesis | en_US |