RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models

• URL: http://arxiv.org/abs/2407.12730v2
• Date: Mon, 25 Nov 2024 02:12:05 GMT
• Title: RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models
• Authors: Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yugang Jiang,
• Abstract summary: Uni-Food is a unified food dataset that comprises over 100,000 images with various food labels. Uni-Food is designed to provide a more holistic approach to food data analysis. We introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach to address the inherent challenges of food-related multitasking.
• Score: 96.43285670458803
• License:
• Abstract: Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, including categories, ingredients, recipes, and ingredient-level nutritional information. Uni-Food is designed to provide a more holistic approach to food data analysis, thereby enhancing the performance and capabilities of LMMs in this domain. To mitigate the conflicts arising from multi-task supervision during fine-tuning of LMMs, we introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach. RoDE utilizes a diverse array of experts to address tasks of varying complexity, thereby facilitating the coordination of trainable parameters, i.e., it allocates more parameters for more complex tasks and, conversely, fewer parameters for simpler tasks. RoDE implements linear rectification union to refine the router's functionality, thereby enhancing the efficiency of sparse task allocation. These design choices endow RoDE with features that ensure GPU memory efficiency and ease of optimization. Our experimental results validate the effectiveness of our proposed approach in addressing the inherent challenges of food-related multitasking.

Related papers

• Retrieval Augmented Recipe Generation [96.43285670458803]
  We propose a retrieval augmented large multimodal model for recipe generation. It retrieves recipes semantically related to the image from an existing datastore as a supplement. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation.
  arXiv  Detail & Related papers  (2024-11-13T15:58:50Z)
• MetaFood3D: Large 3D Food Object Dataset with Nutrition Values [53.24500333363066]
  This dataset consists of 637 meticulously labeled 3D food objects across 108 categories, featuring detailed nutrition information, weight, and food codes linked to a comprehensive nutrition database. Experimental results demonstrate our dataset's significant potential for improving algorithm performance, highlight the challenging gap between video captures and 3D scanned data, and show the strength of the MetaFood3D dataset in high-quality data generation, simulation, and augmentation.
  arXiv  Detail & Related papers  (2024-09-03T15:02:52Z)
• Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection [37.866458336327184]
  Food detection needs Zero-Shot Detection (ZSD) on novel unseen food objects to support real-world scenarios. We first benchmark the task of Zero-Shot Food Detection (ZSFD) by introducing FOWA dataset with rich attribute annotations. We propose a novel framework ZSFDet to tackle fine-grained problems by exploiting the interaction between complex attributes.
  arXiv  Detail & Related papers  (2024-02-14T15:32:35Z)
• FoodLMM: A Versatile Food Assistant using Large Multi-modal Model [96.76271649854542]
  Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities. We introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutritional values and multiple segmentation masks.
  arXiv  Detail & Related papers  (2023-12-22T11:56:22Z)
• When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications [57.342772288710044]
  We propose a novel parameter efficient fine-tuning framework for multi-task medical applications, dubbed as MOELoRA. For unifying MOE and LoRA, we devise multiple experts as the trainable parameters, where each expert consists of a pair of low-rank matrices to retain the small size of trainable parameters. We conduct experiments on a multi-task medical dataset, indicating MOELoRA outperforms the existing parameter efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2023-10-21T17:18:09Z)
• FIRE: Food Image to REcipe generation [10.45344523054623]
  Food computing aims to develop end-to-end intelligent systems capable of autonomously producing recipe information for a food image. This paper proposes FIRE, a novel methodology tailored to recipe generation in the food computing domain. We showcase two practical applications that can benefit from integrating FIRE with large language model prompting.
  arXiv  Detail & Related papers  (2023-08-28T08:14:20Z)
• CHEF: Cross-modal Hierarchical Embeddings for Food Domain Retrieval [20.292467149387594]
  We introduce a novel cross-modal learning framework to jointly model the latent representations of images and text in the food image-recipe association and retrieval tasks. Our experiments show that by making use of efficient tree-structured Long Short-Term Memory as the text encoder in our computational cross-modal retrieval framework, we are able to identify the main ingredients and cooking actions in the recipe descriptions without explicit supervision.
  arXiv  Detail & Related papers  (2021-02-04T11:24:34Z)
• MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model [28.649961369386148]
  We present Modality-Consistent Embedding Network (MCEN) that learns modality-invariant representations by projecting images and texts to the same embedding space. Our method learns the cross-modal alignments during training but computes embeddings of different modalities independently at inference time for the sake of efficiency.
  arXiv  Detail & Related papers  (2020-04-02T16:00:10Z)
• Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism [70.85894675131624]
  We learn an embedding of images and recipes in a common feature space, such that the corresponding image-recipe embeddings lie close to one another. We propose Semantic-Consistent and Attention-based Networks (SCAN), which regularize the embeddings of the two modalities through aligning output semantic probabilities. We show that we can outperform several state-of-the-art cross-modal retrieval strategies for food images and cooking recipes by a significant margin.
  arXiv  Detail & Related papers  (2020-03-09T07:41:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.