Muhammad Ramzan
iamramzan
AI & ML interests
GenAI, Vision & Co
Organizations
Vision Foundation Models 🧩
Foundation models for computer vision.
- RunningAgents126
Grounding DINO Demo
💻126Cutting edge open-vocabulary object detection app
- RunningAgentsFeatured106
Owlv2
👀106State-of-the-art Zero-shot Object Detection
- Configuration errorAgentsFeatured41
BLIP2 with transformers
🌖41BLIP2 (cutting edge image captioning) in 🤗transformers
- Build errorAgentsFeatured376
IDEFICS Playground
🐨376
Comprehensive Computer Vision Backbones 🧩
This collection offers a variety of pre-trained computer vision backbones ideal for fine-tuning.
-
microsoft/resnet-50
Image Classification • 25.6M • Updated • 163k • • 530 -
google/vit-base-patch16-224-in21k
Image Feature Extraction • 86.4M • Updated • 1,000k • 433 -
google/vit-base-patch32-224-in21k
Image Feature Extraction • 88M • Updated • 17.5k • 29 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 626k • 128
Top Vision-Language Papers 🖼️💬📝
A curated list of papers on vision-language models, with the most influential ones at the top.
-
Improved Baselines with Visual Instruction Tuning
Paper • 2310.03744 • Published • 39 -
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper • 2403.05525 • Published • 49 -
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities
Paper • 2308.12966 • Published • 13 -
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
Paper • 2404.01331 • Published • 26
Cutting-Edge Object Detection Models 🥥
-
facebook/detr-resnet-50
Object Detection • 41.6M • Updated • 84.5k • • 991 -
facebook/detr-resnet-101-dc5
Object Detection • 60.7M • Updated • 2.67k • 26 -
facebook/detr-resnet-50-dc5
Object Detection • 41.6M • Updated • 11.4k • 10 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 152k • 159
Shaheen Collection 🦅
Top Vision-Language Papers 🖼️💬📝
A curated list of papers on vision-language models, with the most influential ones at the top.
-
Improved Baselines with Visual Instruction Tuning
Paper • 2310.03744 • Published • 39 -
DeepSeek-VL: Towards Real-World Vision-Language Understanding
Paper • 2403.05525 • Published • 49 -
Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities
Paper • 2308.12966 • Published • 13 -
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
Paper • 2404.01331 • Published • 26
Vision Foundation Models 🧩
Foundation models for computer vision.
- RunningAgents126
Grounding DINO Demo
💻126Cutting edge open-vocabulary object detection app
- RunningAgentsFeatured106
Owlv2
👀106State-of-the-art Zero-shot Object Detection
- Configuration errorAgentsFeatured41
BLIP2 with transformers
🌖41BLIP2 (cutting edge image captioning) in 🤗transformers
- Build errorAgentsFeatured376
IDEFICS Playground
🐨376
Cutting-Edge Object Detection Models 🥥
-
facebook/detr-resnet-50
Object Detection • 41.6M • Updated • 84.5k • • 991 -
facebook/detr-resnet-101-dc5
Object Detection • 60.7M • Updated • 2.67k • 26 -
facebook/detr-resnet-50-dc5
Object Detection • 41.6M • Updated • 11.4k • 10 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 152k • 159
Comprehensive Computer Vision Backbones 🧩
This collection offers a variety of pre-trained computer vision backbones ideal for fine-tuning.
-
microsoft/resnet-50
Image Classification • 25.6M • Updated • 163k • • 530 -
google/vit-base-patch16-224-in21k
Image Feature Extraction • 86.4M • Updated • 1,000k • 433 -
google/vit-base-patch32-224-in21k
Image Feature Extraction • 88M • Updated • 17.5k • 29 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 626k • 128