FoodLogAthl-218: Constructing a Real-World Food Image Dataset Using Dietary Management Applications

TL;DR

This paper introduces FoodLogAthl-218, a real-world food image dataset from dietary apps, enabling more realistic training and evaluation of food classification models with diverse, user-generated images and rich metadata.

Contribution

The creation of FoodLogAthl-218, a large, diverse dataset from real-world meal logs, and the proposal of new tasks including incremental fine-tuning and context-aware classification.

Findings

Models perform well on standard classification tasks.

Incremental fine-tuning improves model adaptation over time.

Context-aware classification enhances dish recognition accuracy.

Abstract

Food image classification models are crucial for dietary management applications because they reduce the burden of manual meal logging. However, most publicly available datasets for training such models rely on web-crawled images, which often differ from users' real-world meal photos. In this work, we present FoodLogAthl-218, a food image dataset constructed from real-world meal records collected through the dietary management application FoodLog Athl. The dataset contains 6,925 images across 218 food categories, with a total of 14,349 bounding boxes. Rich metadata, including meal date and time, anonymized user IDs, and meal-level context, accompany each image. Unlike conventional datasets-where a predefined class set guides web-based image collection-our data begins with user-submitted photos, and labels are applied afterward. This yields greater intra-class diversity, a natural frequency distribution of meal types, and casual, unfiltered images intended for personal use rather than public sharing. In addition to (1) a standard classification benchmark, we introduce two FoodLog-specific tasks: (2) an incremental fine-tuning protocol that follows the temporal stream of users' logs, and (3) a context-aware classification task where each image contains multiple dishes, and the model must classify each dish by leveraging the overall meal context. We evaluate these tasks using large multimodal models (LMMs). The dataset is publicly available at https://huggingface.co/datasets/FoodLog/FoodLogAthl-218.