Salvato in:
Dettagli Bibliografici
Autori principali: Hu, Yue, Zhuang, Guohang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.13889
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915556726145024
author Hu, Yue
Zhuang, Guohang
author_facet Hu, Yue
Zhuang, Guohang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13889
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MultiFoodhat: A potential new paradigm for intelligent food quality inspection
Hu, Yue
Zhuang, Guohang
Computer Vision and Pattern Recognition
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.
title MultiFoodhat: A potential new paradigm for intelligent food quality inspection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.13889