ML Research Wiki / Benchmarks / Visual Question Answering (VQA) / InfographicVQA

InfographicVQA

Visual Question Answering (VQA) Benchmark

Performance Over Time

📊 Showing 21 results | 📏 Metric: ANLS

Top Performing Models

Rank Model Paper ANLS Date Code
1 Gemini Ultra (pixel only) Gemini: A Family of Highly Capable Multimodal Models 80.30 2023-12-19 📦 valdecy/pybibx
2 SMoLA-PaLI-X Specialist 📚 Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts 66.20 2023-12-01 -
3 ScreenAI 5B (4.62 B params, w/ OCR) 📚 ScreenAI: A Vision-Language Model for UI and Infographics Understanding 65.90 2024-02-07 📦 google-research-datasets/screen_qa 📦 google-research-datasets/screen_annotation
4 SMoLA-PaLI-X Generalist 📚 Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts 65.60 2023-12-01 -
5 UDOP (aux) 📚 Unifying Vision, Text, and Layout for Universal Document Processing 63.00 2022-12-05 📦 microsoft/i-code 📦 microsoft/udop 📦 DS4SD/MarkushGrapher 📦 MindCode-4/code-5 📦 pwc-1/Paper-10
6 PaLI-3 (w/ OCR) PaLI-3 Vision Language Models: Smaller, Faster, Stronger 62.40 2023-10-13 📦 kyegomez/PALI3
7 TILT-Large 📚 Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer 61.20 2021-02-18 📦 uakarsh/TiLT-Implementation
8 PaLI-3 PaLI-3 Vision Language Models: Smaller, Faster, Stronger 57.80 2023-10-13 📦 kyegomez/PALI3
9 ChatGPT 3.5 with LAPDoc Prompt (SpatialFormat) LAPDoc: Layout-Aware Prompting for Documents 54.90 2024-02-15 -
10 PaLI-X (Single-task FT w/ OCR) 📚 PaLI-X: On Scaling up a Multilingual Vision and Language Model 54.80 2023-05-29 📦 kyegomez/PALI 📦 doc-doc/NExT-OE

All Papers (21)

valdecy/pybibx
google-research-datasets/screen_qa google-research-datasets/screen_annotation
microsoft/i-code microsoft/udop
kyegomez/PALI3
uakarsh/TiLT-Implementation
kyegomez/PALI3

LAPDoc: Layout-Aware Prompting for Documents

2024
ChatGPT 3.5 with LAPDoc Prompt (SpatialFormat)
kyegomez/PALI doc-doc/NExT-OE
wenjinw/latin-prompt deepopinion/anls-star-metric deepopinion/anls_star_metric
kyegomez/PALI doc-doc/NExT-OE
kyegomez/PALI doc-doc/NExT-OE
wenjinw/latin-prompt deepopinion/anls-star-metric deepopinion/anls_star_metric
uakarsh/docformerv2
microsoft/i-code microsoft/udop
huggingface/transformers google-research/pix2struct
huggingface/transformers google-research/pix2struct
huggingface/transformers