English

FoodLMM: A Versatile Food Assistant using Large Multi-modal Model

Computer Vision and Pattern Recognition 2024-04-15 v2

Abstract

Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. Nevertheless, the performance of general LMMs in specific domains is still far from satisfactory. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation and multi-round conversation. To facilitate FoodLMM to deal with tasks beyond pure text output, we introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutritional values and multiple segmentation masks. We adopt a two-stage training strategy. In the first stage, we utilize multiple public food benchmarks for multi-task learning by leveraging the instruct-following paradigm. In the second stage, we construct a multi-round conversation dataset and a reasoning segmentation dataset to fine-tune the model, enabling it to conduct professional dialogues and generate segmentation masks based on complex reasoning in the food domain. Our fine-tuned FoodLMM achieves state-of-the-art results across several food benchmarks. We will make our code, models and datasets publicly available.

Keywords

Cite

@article{arxiv.2312.14991,
  title  = {FoodLMM: A Versatile Food Assistant using Large Multi-modal Model},
  author = {Yuehao Yin and Huiyan Qi and Bin Zhu and Jingjing Chen and Yu-Gang Jiang and Chong-Wah Ngo},
  journal= {arXiv preprint arXiv:2312.14991},
  year   = {2024}
}
R2 v1 2026-06-28T14:00:19.801Z