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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Yuehao, Qi, Huiyan, Zhu, Bin, Chen, Jingjing, Jiang, Yu-Gang, Ngo, Chong-Wah
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917638446252032
author Yin, Yuehao
Qi, Huiyan
Zhu, Bin
Chen, Jingjing
Jiang, Yu-Gang
Ngo, Chong-Wah
author_facet Yin, Yuehao
Qi, Huiyan
Zhu, Bin
Chen, Jingjing
Jiang, Yu-Gang
Ngo, Chong-Wah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_14991
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FoodLMM: A Versatile Food Assistant using Large Multi-modal Model
Yin, Yuehao
Qi, Huiyan
Zhu, Bin
Chen, Jingjing
Jiang, Yu-Gang
Ngo, Chong-Wah
Computer Vision and Pattern Recognition
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.
title FoodLMM: A Versatile Food Assistant using Large Multi-modal Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.14991