DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910122223075328 |
|---|---|
| author | Jin, Song Zhang, Juntian Zhang, Xun Tian, Zeying Jiang, Fei Yin, Guojun Lin, Wei Liu, Yong Yan, Rui |
| author_facet | Jin, Song Zhang, Juntian Zhang, Xun Tian, Zeying Jiang, Fei Yin, Guojun Lin, Wei Liu, Yong Yan, Rui |
| contents | Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, verification-based nutritional data. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary models. Our experiments reveal that while current VLMs excel at general reasoning, they struggle significantly with fine-grained visual discrimination and precise nutritional reasoning. Furthermore, we systematically investigate the impact of multi-view inputs and Chain-of-Thought reasoning, identifying five primary failure modes. DiningBench serves as a challenging testbed to drive the next generation of food-centric VLM research. All codes are released in https://github.com/meituan/DiningBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10425 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain Jin, Song Zhang, Juntian Zhang, Xun Tian, Zeying Jiang, Fei Yin, Guojun Lin, Wei Liu, Yong Yan, Rui Computer Vision and Pattern Recognition Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, verification-based nutritional data. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary models. Our experiments reveal that while current VLMs excel at general reasoning, they struggle significantly with fine-grained visual discrimination and precise nutritional reasoning. Furthermore, we systematically investigate the impact of multi-view inputs and Chain-of-Thought reasoning, identifying five primary failure modes. DiningBench serves as a challenging testbed to drive the next generation of food-centric VLM research. All codes are released in https://github.com/meituan/DiningBench. |
| title | DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.10425 |