Recursive Visual Programming

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ge, Jiaxin, Subramanian, Sanjay, Shi, Baifeng, Herzig, Roei, Darrell, Trevor
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917718240788480
author Ge, Jiaxin
Subramanian, Sanjay
Shi, Baifeng
Herzig, Roei
Darrell, Trevor
author_facet Ge, Jiaxin
Subramanian, Sanjay
Shi, Baifeng
Herzig, Roei
Darrell, Trevor
contents Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.
format Preprint
id arxiv_https___arxiv_org_abs_2312_02249
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Recursive Visual Programming
Ge, Jiaxin
Subramanian, Sanjay
Shi, Baifeng
Herzig, Roei
Darrell, Trevor
Computer Vision and Pattern Recognition
Computation and Language
Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.
title Recursive Visual Programming
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2312.02249