paper-with-me

홈 › Papers

Oracle Guided Image Synthesis with Relative Queries

2022-04-28 · Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah

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 an oracle 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.

📄 PDF Abstract BibTeX arXiv:2204.14189

Code (1)

helblazer811/oracle-guided-image-synthesis 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

A Theory of Formal Synthesis via Inductive Learning

2015-05-15 · Susmit Jha, Sanjit A. Seshia

Formal synthesis is the process of generating a program satisfying a high-level formal specification. In recent times, effective formal synthesis methods have been proposed based on the use of inductive learning. We refe…

BIG-bench Machine LearningInductive LearningLearning Theory

Satisfiability and Synthesis Modulo Oracles

2021-07-28 · Elizabeth Polgreen, Andrew Reynolds, Sanjit A. Seshia

In classic program synthesis algorithms, such as counterexample-guided inductive synthesis (CEGIS), the algorithms alternate between a synthesis phase and an oracle (verification) phase. Many synthesis algorithms use a w…

Program Synthesis

Oracle-guided Contrastive Clustering

2022-11-01 · Mengdie Wang, Liyuan Shang, Suyun Zhao, Yiming Wang 외

Deep clustering aims to learn a clustering representation through deep architectures. Most of the existing methods usually conduct clustering with the unique goal of maximizing clustering performance, that ignores the pe…

Active LearningClusteringContrastive LearningDeep Clustering

Toward Neural-Network-Guided Program Synthesis and Verification

2021-03-17 · Naoki Kobayashi, Taro Sekiyama, Issei Sato, Hiroshi Unno

We propose a novel framework of program and invariant synthesis called neural network-guided synthesis. We first show that, by suitably designing and training neural networks, we can extract logical formulas over integer…

Program Synthesis

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

2023-12-17 · CVPR 2024 1 · Nikita Starodubcev, Artem Fedorov, Artem Babenko, Dmitry Baranchuk

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods…

Image GenerationKnowledge Distillationtext-guided-image-editing