CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yao, Dongyu, Yao, Keling, Zhou, Junhong, Zhang, Yinghao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929628656959488
author Yao, Dongyu
Yao, Keling
Zhou, Junhong
Zhang, Yinghao
author_facet Yao, Dongyu
Yao, Keling
Zhou, Junhong
Zhang, Yinghao
contents The obesity phenomenon, known as the heavy issue, is a leading cause of preventable chronic diseases worldwide. Traditional calorie estimation tools often rely on specific data formats or complex pipelines, limiting their practicality in real-world scenarios. Recently, vision-language models (VLMs) have excelled in understanding real-world contexts and enabling conversational interactions, making them ideal for downstream tasks such as ingredient analysis. However, applying VLMs to calorie estimation requires domain-specific data and alignment strategies. To this end, we curated CalData, a 330K image-text pair dataset tailored for ingredient recognition and calorie estimation, combining a large-scale recipe dataset with detailed nutritional instructions for robust vision-language training. Built upon this dataset, we present CaLoRAify, a novel VLM framework aligning ingredient recognition and calorie estimation via training with visual-text pairs. During inference, users only need a single monocular food image to estimate calories while retaining the flexibility of agent-based conversational interaction. With Low-rank Adaptation (LoRA) and Retrieve-augmented Generation (RAG) techniques, our system enhances the performance of foundational VLMs in the vertical domain of calorie estimation. Our code and data are fully open-sourced at https://github.com/KennyYao2001/16824-CaLORAify.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09936
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models
Yao, Dongyu
Yao, Keling
Zhou, Junhong
Zhang, Yinghao
Computer Vision and Pattern Recognition
68T07, 68U35
I.2.10; I.2.6; I.5.4
The obesity phenomenon, known as the heavy issue, is a leading cause of preventable chronic diseases worldwide. Traditional calorie estimation tools often rely on specific data formats or complex pipelines, limiting their practicality in real-world scenarios. Recently, vision-language models (VLMs) have excelled in understanding real-world contexts and enabling conversational interactions, making them ideal for downstream tasks such as ingredient analysis. However, applying VLMs to calorie estimation requires domain-specific data and alignment strategies. To this end, we curated CalData, a 330K image-text pair dataset tailored for ingredient recognition and calorie estimation, combining a large-scale recipe dataset with detailed nutritional instructions for robust vision-language training. Built upon this dataset, we present CaLoRAify, a novel VLM framework aligning ingredient recognition and calorie estimation via training with visual-text pairs. During inference, users only need a single monocular food image to estimate calories while retaining the flexibility of agent-based conversational interaction. With Low-rank Adaptation (LoRA) and Retrieve-augmented Generation (RAG) techniques, our system enhances the performance of foundational VLMs in the vertical domain of calorie estimation. Our code and data are fully open-sourced at https://github.com/KennyYao2001/16824-CaLORAify.
title CaLoRAify: Calorie Estimation with Visual-Text Pairing and LoRA-Driven Visual Language Models
topic Computer Vision and Pattern Recognition
68T07, 68U35
I.2.10; I.2.6; I.5.4
url https://arxiv.org/abs/2412.09936