Summary of Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-modal Models, by Pengkun Jiao et al.
RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models
by Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yugang Jiang
First submitted to arxiv on: 17 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes Uni-Food, a unified food dataset containing over 100,000 images with various labels including categories, ingredients, recipes, and nutritional information. This dataset aims to provide a more comprehensive approach to food data analysis, enhancing the performance of Large Multi-modal Models (LMMs) in this domain. Additionally, the paper introduces RoDE, a novel approach for mitigating conflicts arising from multi-task supervision during fine-tuning of LMMs. RoDE utilizes diverse experts to address tasks of varying complexity and implements linear rectification union to refine the router’s functionality. Experimental results validate the effectiveness of Uni-Food and RoDE in addressing food-related multitasking challenges. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new dataset called Uni-Food that combines information about different types of food, including pictures, ingredients, recipes, and nutritional facts. This will help computers understand more about food and be able to perform tasks like recognizing what’s in a recipe or identifying healthy foods. The paper also proposes a new way to train computer models, called RoDE, which helps them learn to do multiple tasks at once without getting confused. |
Keywords
» Artificial intelligence » Fine tuning » Multi modal » Multi task
