Title:
Oracle Guided Image Synthesis with Relative Queries
Oracle Guided Image Synthesis with Relative Queries
| dc.contributor.author | Helbling, Alec Fisher | |
| dc.contributor.committeeMember | Rozell, Christopher | |
| dc.contributor.committeeMember | Riedl, Mark | |
| dc.contributor.department | Computer Science | |
| dc.date.accessioned | 2023-01-19T21:36:17Z | |
| dc.date.available | 2023-01-19T21:36:17Z | |
| dc.date.created | 2022-12 | |
| dc.date.issued | 2023-01-18 | |
| dc.date.submitted | December 2022 | |
| dc.date.updated | 2023-01-19T21:36:18Z | |
| dc.description.abstract | Isolating and controlling specific features in the outputs of generative models in a user-friendly way is a difficult and open-ended problem. We develop techniques that allow a user to generate an image they are envisioning in their head by answering a sequence of relative queries of the form "do you prefer image a or image b?" Our framework consists of a Conditional VAE that uses the collected relative queries to partition the latent space into preference-relevant features and non-preference-relevant features. We then use the user's responses to relative queries to determine the preference-relevant features that correspond to their envisioned output image. Additionally, we develop techniques for modeling the uncertainty in images' predicted preference-relevant features, allowing our framework to generalize to scenarios in which the relative query training set contains noise. | |
| dc.description.degree | Undergraduate | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1853/70229 | |
| dc.language.iso | en_US | |
| dc.publisher | Georgia Institute of Technology | |
| dc.subject | Machine Learning | |
| dc.subject | Generative Modeling | |
| dc.title | Oracle Guided Image Synthesis with Relative Queries | |
| dc.type | Text | |
| dc.type.genre | Undergraduate Thesis | |
| dspace.entity.type | Publication | |
| local.contributor.corporatename | College of Computing | |
| local.contributor.corporatename | School of Computer Science | |
| local.contributor.corporatename | Undergraduate Research Opportunities Program | |
| local.relation.ispartofseries | Undergraduate Research Option Theses | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
| relation.isOrgUnitOfPublication | 6b42174a-e0e1-40e3-a581-47bed0470a1e | |
| relation.isOrgUnitOfPublication | 0db885f5-939b-4de1-807b-f2ec73714200 | |
| relation.isSeriesOfPublication | e1a827bd-cf25-4b83-ba24-70848b7036ac | |
| thesis.degree.level | Undergraduate |