Meta-Learning-Based Lightweight Method for Food Calorie Estimation

As a significant research component in nutritional assessment, vision-based food calorie estimation has been studied and applied due to its higher accuracy and efficiency. In this paper, a lightweight network for food calorie estimation is designed, called MeLL-cal. Firstly, a feature extraction mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinlin Ma, Yuetong Wan, Ziping Ma
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Journal of Food Quality
Online Access:http://dx.doi.org/10.1155/jfq/7044178
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850034041415270400
author Jinlin Ma
Yuetong Wan
Ziping Ma
author_facet Jinlin Ma
Yuetong Wan
Ziping Ma
author_sort Jinlin Ma
collection DOAJ
description As a significant research component in nutritional assessment, vision-based food calorie estimation has been studied and applied due to its higher accuracy and efficiency. In this paper, a lightweight network for food calorie estimation is designed, called MeLL-cal. Firstly, a feature extraction module is proposed based on meta-learning ideas to generate informative representations, such as color, texture, and edge features, for unseen foods. Secondly, within the feature extraction module, a large convolutional kernel is proposed to provide a larger receptive field, which aims to capture more shape and semantic information and minimize information loss. Then, to achieve efficient calorie estimation with lower computational complexity, the calorie estimation module employs query-based inference to achieve optimal feature expression. Additionally, an adaptive fine-tuning module is also designed to refine estimation accuracy according to different datasets. The extensive experiments demonstrate the superiority of the MeLL-cal in terms of a PMAE of 18.7% and 31.1%, respectively, with only 2.313K parameters and 1.036 ms inference time on the Menu match dataset and the Calo world dataset.
format Article
id doaj-art-832430e1637640a2a3fea5f62e9636a8
institution DOAJ
issn 1745-4557
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Journal of Food Quality
spelling doaj-art-832430e1637640a2a3fea5f62e9636a82025-08-20T02:57:57ZengWileyJournal of Food Quality1745-45572025-01-01202510.1155/jfq/7044178Meta-Learning-Based Lightweight Method for Food Calorie EstimationJinlin Ma0Yuetong Wan1Ziping Ma2School of Computer Science and EngineeringSchool of Computer Science and EngineeringSchool of Mathematics and Information ScienceAs a significant research component in nutritional assessment, vision-based food calorie estimation has been studied and applied due to its higher accuracy and efficiency. In this paper, a lightweight network for food calorie estimation is designed, called MeLL-cal. Firstly, a feature extraction module is proposed based on meta-learning ideas to generate informative representations, such as color, texture, and edge features, for unseen foods. Secondly, within the feature extraction module, a large convolutional kernel is proposed to provide a larger receptive field, which aims to capture more shape and semantic information and minimize information loss. Then, to achieve efficient calorie estimation with lower computational complexity, the calorie estimation module employs query-based inference to achieve optimal feature expression. Additionally, an adaptive fine-tuning module is also designed to refine estimation accuracy according to different datasets. The extensive experiments demonstrate the superiority of the MeLL-cal in terms of a PMAE of 18.7% and 31.1%, respectively, with only 2.313K parameters and 1.036 ms inference time on the Menu match dataset and the Calo world dataset.http://dx.doi.org/10.1155/jfq/7044178
spellingShingle Jinlin Ma
Yuetong Wan
Ziping Ma
Meta-Learning-Based Lightweight Method for Food Calorie Estimation
Journal of Food Quality
title Meta-Learning-Based Lightweight Method for Food Calorie Estimation
title_full Meta-Learning-Based Lightweight Method for Food Calorie Estimation
title_fullStr Meta-Learning-Based Lightweight Method for Food Calorie Estimation
title_full_unstemmed Meta-Learning-Based Lightweight Method for Food Calorie Estimation
title_short Meta-Learning-Based Lightweight Method for Food Calorie Estimation
title_sort meta learning based lightweight method for food calorie estimation
url http://dx.doi.org/10.1155/jfq/7044178
work_keys_str_mv AT jinlinma metalearningbasedlightweightmethodforfoodcalorieestimation
AT yuetongwan metalearningbasedlightweightmethodforfoodcalorieestimation
AT zipingma metalearningbasedlightweightmethodforfoodcalorieestimation