Robust Deep Semi-supervised Clustering with Cauchy Mixture

dc.contributor.advisorOates, James T Chapman, David
dc.contributor.authorPatel, Jay Dhirajlal
dc.contributor.departmentComputer Science and Electrical Engineering
dc.contributor.programComputer Science
dc.date.accessioned2023-04-05T14:17:23Z
dc.date.available2023-04-05T14:17:23Z
dc.date.issued2022-01-01
dc.description.abstractIn this paper, we present using Cauchy Mixture Model (CMM) as the activation function of deep neural networks for pseudo-labeling in semi-supervised classification. Unlike SoftMax, which is universally used as the final layer activation function, CMM allows the model to identify outliers, i.e., any data that is out of distribution from the observed data. Furthermore, using CMM for pseudo-labeling provides enhanced robustness against confounding bias by preventing the model from yielding high confidence predictions for out-of-distribution data. The proposed method is trained and tested on the CIFAR-10 dataset using only 250, 1000, and 4000 labels. Compared to the baseline of SoftMax-based only supervised and semi-supervised models, the proposed method shows substantial improvements in the same environment setting.
dc.formatapplication:pdf
dc.genretheses
dc.identifierdoi:10.13016/m2pvrv-qe8a
dc.identifier.other12652
dc.identifier.urihttp://hdl.handle.net/11603/27350
dc.languageen
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Collection
dc.relation.ispartofUMBC Theses and Dissertations Collection
dc.relation.ispartofUMBC Graduate School Collection
dc.relation.ispartofUMBC Student Collection
dc.sourceOriginal File Name: Patel_umbc_0434M_12652.pdf
dc.subjectCauchy Mixture Model
dc.subjectDeep Learning
dc.subjectDeep semi-supervised
dc.subjectMachine Learning
dc.subjectOutlier
dc.subjectSemi supervised Learning
dc.titleRobust Deep Semi-supervised Clustering with Cauchy Mixture
dc.typeText
dcterms.accessRightsDistribution Rights granted to UMBC by the author.
dcterms.accessRightsThis item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Patel_umbc_0434M_12652.pdf
Size:
2.5 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Patel-Jay Dhirajlal_Open.pdf
Size:
80.19 KB
Format:
Adobe Portable Document Format
Description: