Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering
Computer Vision and Pattern Recognition
2024-03-25 v1 Artificial Intelligence
Computation and Language
Machine Learning
Multiagent Systems
Abstract
This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks. We propose an adaptive multi-agent system, named Multi-Agent VQA, to overcome the limitations of foundation models in object detection and counting by using specialized agents as tools. Unlike existing approaches, our study focuses on the system's performance without fine-tuning it on specific VQA datasets, making it more practical and robust in the open world. We present preliminary experimental results under zero-shot scenarios and highlight some failure cases, offering new directions for future research.
Cite
@article{arxiv.2403.14783,
title = {Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering},
author = {Bowen Jiang and Zhijun Zhuang and Shreyas S. Shivakumar and Dan Roth and Camillo J. Taylor},
journal= {arXiv preprint arXiv:2403.14783},
year = {2024}
}
Comments
A full version of the paper will be released soon. The codes are available at https://github.com/bowen-upenn/Multi-Agent-VQA