Zobrazit v EDS

From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios

Uloženo v:
Podrobná bibliografie
Název: From Canteen Food to Daily Meals: Generalizing Food Recognition to More Practical Scenarios
Autoři: Guoshan Liu, Yang Jiao, Jingjing Chen, Bin Zhu, Yu-Gang Jiang
Zdroj: IEEE Transactions on Multimedia. 27:2724-2733
Publication Status: Preprint
Informace o vydavateli: Institute of Electrical and Electronics Engineers (IEEE), 2025.
Rok vydání: 2025
Témata: FOS: Computer and information sciences, 2. Zero hunger, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Food datasets, Computer Vision and Pattern Recognition (cs.CV), Graphics and Human Computer Interfaces, Food recognition, Computer Science - Computer Vision and Pattern Recognition, 0202 electrical engineering, electronic engineering, information engineering, Unsupervised Domain Adaptation, 02 engineering and technology
Popis: The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant research attention in recent years. Prominent benchmarks, such as Food-101 and VIREO Food-172, provide abundant food image resources that catalyze the prosperity of research in this field. Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. This discrepancy poses great challenges in effectively transferring classifiers trained on these canteen datasets to broader daily-life scenarios encountered by humans. Toward this end, we present two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from everyday meals. These two datasets are used to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain. In addition, we also propose a simple yet effective baseline method named Multi-Cluster Reference Learning (MCRL) to tackle the aforementioned domain gap. MCRL is motivated by the observation that food images in daily-life scenarios exhibit greater intra-class appearance variance compared with those in well-curated benchmarks. Notably, MCRL can be seamlessly coupled with existing approaches, yielding non-trivial performance enhancements. We hope our new benchmarks can inspire the community to explore the transferability of food recognition models trained on well-curated datasets toward practical real-life applications.
Druh dokumentu: Article
Popis souboru: application/pdf
ISSN: 1941-0077
1520-9210
DOI: 10.1109/tmm.2024.3371212
DOI: 10.48550/arxiv.2403.07403
Přístupová URL adresa: http://arxiv.org/abs/2403.07403
Rights: IEEE Copyright
arXiv Non-Exclusive Distribution
CC BY NC ND
Přístupové číslo: edsair.doi.dedup.....75e669786955f41450582f0060cb0bad
Databáze: OpenAIRE
Popis
Abstrakt:The precise recognition of food categories plays a pivotal role for intelligent health management, attracting significant research attention in recent years. Prominent benchmarks, such as Food-101 and VIREO Food-172, provide abundant food image resources that catalyze the prosperity of research in this field. Nevertheless, these datasets are well-curated from canteen scenarios and thus deviate from food appearances in daily life. This discrepancy poses great challenges in effectively transferring classifiers trained on these canteen datasets to broader daily-life scenarios encountered by humans. Toward this end, we present two new benchmarks, namely DailyFood-172 and DailyFood-16, specifically designed to curate food images from everyday meals. These two datasets are used to evaluate the transferability of approaches from the well-curated food image domain to the everyday-life food image domain. In addition, we also propose a simple yet effective baseline method named Multi-Cluster Reference Learning (MCRL) to tackle the aforementioned domain gap. MCRL is motivated by the observation that food images in daily-life scenarios exhibit greater intra-class appearance variance compared with those in well-curated benchmarks. Notably, MCRL can be seamlessly coupled with existing approaches, yielding non-trivial performance enhancements. We hope our new benchmarks can inspire the community to explore the transferability of food recognition models trained on well-curated datasets toward practical real-life applications.
ISSN:19410077
15209210
DOI:10.1109/tmm.2024.3371212