Show simple item record

Semi-supervised framework for clustering and semantic segmentation

dc.contributor.advisorYang, Yimin
dc.contributor.advisorDu, Shan
dc.contributor.authorChow, Yik Lun
dc.date.accessioned2021-10-01T13:52:34Z
dc.date.available2021-10-01T13:52:34Z
dc.date.created2021
dc.date.issued2021
dc.identifier.urihttps://knowledgecommons.lakeheadu.ca/handle/2453/4865
dc.description.abstractDuring the past couple of decades, machine learning and deep learning methods have achieved remarkable results in many real-world applications. However, it is difficult to develop and train these artificial intelligence algorithms without a labeled dataset. Under this circumstance, it is desirable to leverage a large number of unlabeled data into the training process with fewer or even without labels. To this end, a non-supervised learning strategy (e.g., unsupervised, semi-supervised, weakly-supervised, or self-supervised) has recently been studied in different domains. In chapter 3, a novel semi-supervised framework is proposed to solve a clustering problem fundamentally by involving only few numbers of labeled data. In this proposed framework, a non-iterative autoencoder is proposed for learning a representation of each data in an unsupervised way. The experimental results theoretically demonstrate the effectiveness of this proposed framework, where the obtained clustering accuracy for thirteen tabular and image datasets are impressive. It has also shown that the proposed autoencoder is able to capture important features of each data. In chapter 4, the above framework is extended to a weakly-supervised semantic segmentation task for demonstrating its practical ability. Before applying the modified proposed framework to this task, computer vision methods are presented as preliminary work to generate the initial labeled data and clustering space. We achieve the current state-of-the-art performance on PASCAL VOC 2012 dataset. This thesis shows that the proposed framework is capable not only for the traditional machine learning problem but also for the widely used real-world applications.en_US
dc.language.isoen_USen_US
dc.subjectUnsupervised representation learningen_US
dc.subjectNon-iterative autoencoderen_US
dc.subjectSemi-supervised clusteringen_US
dc.subjectSemantic segmentationen_US
dc.titleSemi-supervised framework for clustering and semantic segmentationen_US
dc.typeThesisen_US
etd.degree.nameMaster of Scienceen_US
etd.degree.levelMasteren_US
etd.degree.disciplineComputer Scienceen_US
etd.degree.grantorLakehead Universityen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record