Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering
This work addresses zero-shot VQA for practical open-world applications, but it is incremental as it builds on existing foundation models with specialized agents.
The paper tackled the problem of zero-shot Visual Question Answering (VQA) by proposing a multi-agent system to address limitations in object detection and counting, achieving preliminary results without fine-tuning on specific datasets.
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.