FoodLMM: A Versatile Food Assistant using Large Multi-modal Model
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Classification | Food101 | Top-1 Accuracy93.93 | 83 | |
| Recipe Generation | Recipe1M | SacreBLEU6.24 | 12 | |
| Calorie estimation | CalorieBench-80K (test) | MAE170.3 | 9 | |
| Dietary advice generation | CalorieBench 80K | ROUGE-10.23 | 9 | |
| Ingredient Recognition | VireoFood-172 | F1 Score68.97 | 4 | |
| Nutrition Estimation | Nutrition5k (test) | Calorie pMAE26.6 | 3 | |
| Referring Nutrition Estimation | Nutrition5k refer@1st 1.0 (test) | Calorie MAE25.2 | 2 | |
| Referring Nutrition Estimation | Nutrition5k refer@2nd 1.0 (test) | Calorie MAE21 | 2 | |
| Referring Nutrition Estimation | Nutrition5k refer@3rd 1.0 (test) | Calorie MAE16.9 | 2 |