AI2 Diagrams
AI2 Diagrams (AI2D) is a dataset of over 5000 grade school science diagrams with over 150000 rich annotations, their ground truth syntactic parses, and more than 15000 corresponding multiple choice questions.
Source: A Diagram Is Worth A Dozen Images
Image Source: Kembhavi et al
Variants: AI2D
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Question Answering (VQA) | Gemini Ultra | Gemini: A Family of Highly … | 2023-12-19 |
| Visual Question Answering (VQA) | SMoLA-PaLI-X Generalist Model | Omni-SMoLA: Boosting Generalist Multimodal Models … | 2023-12-01 |
| Visual Question Answering (VQA) | SMoLA-PaLI-X Specialist Model | Omni-SMoLA: Boosting Generalist Multimodal Models … | 2023-12-01 |
| Visual Question Answering (VQA) | DUBLIN | DUBLIN -- Document Understanding By … | 2023-05-23 |
Recent papers with results on this dataset: