Methods for generating visual programs with optimizable vision models

Levine, Joshua

Permalink

https://hdl.handle.net/2142/124357 Copy

Description

Title

Methods for generating visual programs with optimizable vision models

Author(s)

Levine, Joshua

Issue Date

2024-04-29

Director of Research (if dissertation) or Advisor (if thesis)

Hoiem, Derek

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Visual Programming
• Visual Question Answering
• Large Language Models
• Computer Vision
• Program Generation

Language

eng

Abstract

End-to-end vision-language models often fail to handle compositional tasks, necessitating alternative approaches for more complex problem-solving. Leveraging the visual programming paradigm, we propose a novel method for composing foundational vision models through program generation to tackle compositional tasks effectively. We investigate prompting and execution strategies that enable the synthesis of fine-tunable code by trainable large language models aimed at improving the effectiveness of the programs in solving vision-language tasks. Capitalizing on the robust compositional reasoning capabilities of large language models (LLMs), we employ pre-trained LLMs to architect programs constructed using a catalog of pre-defined atomic functions. These atomic functions, implemented with pre-trained vision models, serve as the building blocks for the visual programs generated by our system. Our methodology supports programs in various formats, always offering the flexibility to fine-tune the constituent vision models and the LLM code generator. This study concentrates on image-based question-answering. This focus underscores the critical need for advanced compositional reasoning in interpreting and responding to complex visual queries. Our evaluation encompasses the executability and correctness of the produced programs, providing a comprehensive assessment of our approach's effectiveness. This paper lays the groundwork for a subsequent investigation into the joint training of the LLMs and atomic functions, setting the stage for significant advancements in program generation and compositional reasoning in computer vision.

Graduation Semester

2024-05

Type of Resource

Text

Handle URL

https://hdl.handle.net/2142/124357

Copyright and License Information

Copyright 2024 Joshua Levine

Owning Collections