ColFlor: Towards BERT-Size Vision-Language Document Retrieval Models
•
16
Ahmed Masry PRO
ahmed-masry
AI & ML interests
Multimodal Chart Understanding,
Multimodal Document AI,
Multimodal Vision - Language Models,
Recent Activity
liked
a dataset
3 days ago
MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
new activity
6 days ago
ahmed-masry/unichart-qa-data:Dataset Source?
liked
a dataset
12 days ago
ServiceNow/BigDocs-Bench
Articles
Organizations
None yet
ahmed-masry's activity
liked
a
dataset
3 days ago
Dataset Source?
4
#3 opened 6 days ago
by
veason
liked
a
dataset
12 days ago
authored
a
paper
about 1 month ago
upvoted
a
paper
about 1 month ago
Update README.md
1
#1 opened 2 months ago
by
omkar334
updated
a
model
3 months ago
reacted to
merve's
post with 🚀
3 months ago
Post
1976
It's raining depth estimation models ☔️
DepthPro is a zero-shot depth estimation model by Apple, it's fast, sharp and accurate 🔥
Demo: akhaliq/depth-pro
Model: apple/DepthPro
Paper page: Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2410.02073)
The model consists of two encoders: an encoder for patches and an image encoder 🖼️ The outputs of both are merged to decode to depth maps and get the focal length.
The model outperforms the previous state-of-the-art models in average of various benchmarks 📑
DepthPro is a zero-shot depth estimation model by Apple, it's fast, sharp and accurate 🔥
Demo: akhaliq/depth-pro
Model: apple/DepthPro
Paper page: Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (2410.02073)
The model consists of two encoders: an encoder for patches and an image encoder 🖼️ The outputs of both are merged to decode to depth maps and get the focal length.
The model outperforms the previous state-of-the-art models in average of various benchmarks 📑
posted
an
update
3 months ago
Post
1348
🚀 Introducing ColFlor: An Efficient, OCR-Free Vision-Language Document Retrieval Model 🌟
Earlier this year, ColPali revolutionized document retrieval by eliminating the need for error-prone OCR pipelines. Instead, it directly processes the document images. However, with its 3 billion parameters, ColPali is computationally heavy for large-scale applications.
That’s where ColFlor comes in—a smaller, faster alternative! 🎉 At 17x smaller than ColPali, ColFlor offers a more efficient, OCR-free document retrieval solution, making it ideal for users with limited computing resources (GPU Poor). 💡
Key Highlights:
🧠 174M parameters (vs. 3B for ColPali)
⚡ 9.8x faster query encoding, 5.25x faster image encoding
📉 Only 1.8% performance drop on text-rich English documents
Check out the full blog post for more insights on modeling, training, and evaluations across various document retrieval tasks! 🚀
Also, feel free to try our demo on huggingface 🤗
🔗 Resources:
📄 Blog post: https://huggingface.co/blog/ahmed-masry/colflor
🧠 Model: ahmed-masry/ColFlor
💻 Demo: ahmed-masry/ColFlor-Demo
🏋️♂️ Training code: https://github.com/AhmedMasryKU/colflor
📊 Evaluation code: https://github.com/AhmedMasryKU/vidore-benchmark-colflor
Earlier this year, ColPali revolutionized document retrieval by eliminating the need for error-prone OCR pipelines. Instead, it directly processes the document images. However, with its 3 billion parameters, ColPali is computationally heavy for large-scale applications.
That’s where ColFlor comes in—a smaller, faster alternative! 🎉 At 17x smaller than ColPali, ColFlor offers a more efficient, OCR-free document retrieval solution, making it ideal for users with limited computing resources (GPU Poor). 💡
Key Highlights:
🧠 174M parameters (vs. 3B for ColPali)
⚡ 9.8x faster query encoding, 5.25x faster image encoding
📉 Only 1.8% performance drop on text-rich English documents
Check out the full blog post for more insights on modeling, training, and evaluations across various document retrieval tasks! 🚀
Also, feel free to try our demo on huggingface 🤗
🔗 Resources:
📄 Blog post: https://huggingface.co/blog/ahmed-masry/colflor
🧠 Model: ahmed-masry/ColFlor
💻 Demo: ahmed-masry/ColFlor-Demo
🏋️♂️ Training code: https://github.com/AhmedMasryKU/colflor
📊 Evaluation code: https://github.com/AhmedMasryKU/vidore-benchmark-colflor
updated
a
Space
3 months ago
liked
a
dataset
3 months ago
published
an
article
3 months ago
Article
ColFlor: Towards BERT-Size Vision-Language Document Retrieval Models
By
•
•
16
how the handle hallucination?
1
#2 opened 5 months ago
by
RaushanA
updated
a
dataset
5 months ago
liked
a
Space
5 months ago
updated
a
dataset
5 months ago
Missing license
1
#1 opened 6 months ago
by
maskedviper
updated
a
model
6 months ago
commented
a
paper
6 months ago