Oracle Guided Image Synthesis with Relative Queries

Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah

Keywords: Variational Autoencoder, Image Synthesis, Relative Attributes, Paired Comparisons, Triplet Loss, Structured latent representations, Human-Computer Interaction

TL;DR: We describe a method for performing guided image synthesis with a VAE by asking users queries of the form "do you prefer image A or image B?"

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 \textit{``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.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2204.14189/code)