Weakly supervised object localization using attention-based neural networks

Simple item page
dc.contributor.authorTeh, Eu Wern
dc.contributor.examiningcommitteeBruce, Neil (Computer Science) Hu, Pingzhao (Biochemistry and Medical Genetics)en_US
dc.contributor.supervisorWang, Yang (Computer Science)en_US
dc.date.accessioned2017-06-27T13:46:41Z
dc.date.available2017-06-27T13:46:41Z
dc.date.issued2016en_US
dc.degree.disciplineComputer Scienceen_US
dc.degree.levelMaster of Science (M.Sc.)en_US
dc.description.abstractWe consider the problem of weakly supervised learning for object localization. Given a collection of images with image-level annotations indicating the presence/absence of an object, our goal is to localize the object in each image. We propose a neural network architecture called the attention network for this problem. In addition to the attention network, we also propose three extensions. Firstly, we propose an ap- proach to regularized the attention scores so that it mimics the scoring distribution of a strong fully supervised object detector. Secondly, we also propose an approach to iteratively refined the result of our attention network. Lastly, we propose to combine both first and second extensions into a single network to achieve the best of both worlds. We demonstrate that all of our approaches achieve superior performance on several benchmark datasets.en_US
dc.description.noteOctober 2017en_US
dc.identifier.citationMLAen_US
dc.identifier.urihttp://hdl.handle.net/1993/32280
dc.language.isoengen_US
dc.publisherBritish Machine Vision Conferenceen_US
dc.rightsopen accessen_US
dc.subjectNeural networken_US
dc.subjectObject localizationen_US
dc.subjectObject detectionen_US
dc.subjectWeakly supervised learningen_US
dc.titleWeakly supervised object localization using attention-based neural networksen_US
dc.typemaster thesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis.pdf
Size:
64.14 MB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.2 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica