Title:
Oracle Guided Image Synthesis with Relative Queries
Oracle Guided Image Synthesis with Relative Queries
Author(s)
Helbling, Alec Fisher
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
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.
Sponsor
Date Issued
2023-01-18
Extent
Resource Type
Text
Resource Subtype
Undergraduate Thesis