Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.09966 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908488152645632 |
|---|---|
| author | Hosseinian, Amir Zahedani, Ashkan Dehghani Mansoor, Umer Hashemi, Noosheen Woodward, Mark |
| author_facet | Hosseinian, Amir Zahedani, Ashkan Dehghani Mansoor, Umer Hashemi, Noosheen Woodward, Mark |
| contents | Progress in AI for automated nutritional analysis is critically hampered by the lack of standardized evaluation methodologies and high-quality, real-world benchmark datasets. To address this, we introduce three primary contributions. First, we present the January Food Benchmark (JFB), a publicly available collection of 1,000 food images with human-validated annotations. Second, we detail a comprehensive benchmarking framework, including robust metrics and a novel, application-oriented overall score designed to assess model performance holistically. Third, we provide baseline results from both general-purpose Vision-Language Models (VLMs) and our own specialized model, january/food-vision-v1. Our evaluation demonstrates that the specialized model achieves an Overall Score of 86.2, a 12.1-point improvement over the best-performing general-purpose configuration. This work offers the research community a valuable new evaluation dataset and a rigorous framework to guide and benchmark future developments in automated nutritional analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09966 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis Hosseinian, Amir Zahedani, Ashkan Dehghani Mansoor, Umer Hashemi, Noosheen Woodward, Mark Computer Vision and Pattern Recognition Artificial Intelligence Progress in AI for automated nutritional analysis is critically hampered by the lack of standardized evaluation methodologies and high-quality, real-world benchmark datasets. To address this, we introduce three primary contributions. First, we present the January Food Benchmark (JFB), a publicly available collection of 1,000 food images with human-validated annotations. Second, we detail a comprehensive benchmarking framework, including robust metrics and a novel, application-oriented overall score designed to assess model performance holistically. Third, we provide baseline results from both general-purpose Vision-Language Models (VLMs) and our own specialized model, january/food-vision-v1. Our evaluation demonstrates that the specialized model achieves an Overall Score of 86.2, a 12.1-point improvement over the best-performing general-purpose configuration. This work offers the research community a valuable new evaluation dataset and a rigorous framework to guide and benchmark future developments in automated nutritional analysis. |
| title | January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09966 |