用对话式多智能体实现零样本食物识别，无需标注数据
MultiFoodhat: A potential new paradigm for intelligent food quality inspection
- 通过视觉语言模型与大模型对话协作，动态推理食物特征
- 在多个公开数据集上表现优于现有无监督和少样本方法
- 适合需要快速适配新食物种类的智能质检场景
食物图像分类在智能食物质量检测、膳食评估和自动监控中至关重要。然而，现有大多数监督模型依赖大规模标注数据，对未见食物类别泛化能力有限。为此，本文提出 MultiFoodChat，一种基于对话的多智能体推理框架，用于零样本食物识别。该框架融合视觉语言模型（VLMs）与大语言模型（LLMs），通过多轮视觉-文本对话实现协同推理。引入物体感知令牌（OPT）捕捉细粒度视觉属性，交互式推理代理（IRA）动态解析上下文线索以优化预测。这种多智能体设计使系统能在不额外训练或人工标注的前提下，灵活实现类人对复杂食物场景的理解。在多个公开食物数据集上的实验表明，MultiFoodChat 在识别准确率和可解释性方面均优于现有无监督与少样本方法，展现出作为智能食物质量检测新范式的潜力。
原文摘要 · Abstract (English)
Food image classification plays a vital role in intelligent food quality inspection, dietary assessment, and automated monitoring. However, most existing supervised models rely heavily on large labeled datasets and exhibit limited generalization to unseen food categories. To overcome these challenges, this study introduces MultiFoodChat, a dialogue-driven multi-agent reasoning framework for zero-shot food recognition. The framework integrates vision-language models (VLMs) and large language models (LLMs) to enable collaborative reasoning through multi-round visual-textual dialogues. An Object Perception Token (OPT) captures fine-grained visual attributes, while an Interactive Reasoning Agent (IRA) dynamically interprets contextual cues to refine predictions. This multi-agent design allows flexible and human-like understanding of complex food scenes without additional training or manual annotations. Experiments on multiple public food datasets demonstrate that MultiFoodChat achieves superior recognition accuracy and interpretability compared with existing unsupervised and few-shot methods, highlighting its potential as a new paradigm for intelligent food quality inspection and analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。