merve PRO
merve
AI & ML interests
I love this website
VLMs, vision & co
Recent Activity
upvoted an article 1 day ago
Mixture of Experts (MoEs) in Transformers published an
article
2 days ago
Mixture of Experts (MoEs) in Transformers published
a model 3 days ago
merve/rtdetr-v2-r50-mobile-ui-design-local Organizations
YOLO26 models: detection, segmentation, classification, pose, and OBB variants with demos and ONNX variants.
-
NVLM: Open Frontier-Class Multimodal LLMs
Paper • 2409.11402 • Published • 74 -
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 19 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 48 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121
Models mentioned in https://huggingface.co/papers/2404.07204
-
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 774k • 102 -
google/flan-t5-xl
3B • Updated • 207k • 528 -
google/siglip-large-patch16-384
Zero-Shot Image Classification • 0.7B • Updated • 18.1k • 11 -
google/vit-huge-patch14-224-in21k
Image Feature Extraction • 0.6B • Updated • 26.7k • 22
-
facebook/deit-base-distilled-patch16-384
Image Classification • 87.6M • Updated • 92.5k • • 7 -
facebook/convnextv2-base-1k-224
Image Classification • 88.7M • Updated • 1.27k • • 4 -
facebook/deit-base-distilled-patch16-224
Image Classification • Updated • 5.28k • • 32 -
google/vit-base-patch32-384
Image Classification • 88.3M • Updated • 4.44k • • 23
A collection of instance/semantic/panoptic segmentation models.
-
facebook/maskformer-swin-large-coco
Image Segmentation • 0.2B • Updated • 472 • 27 -
nvidia/segformer-b0-finetuned-ade-512-512
Image Segmentation • 3.75M • Updated • 606k • • 179 -
facebook/detr-resnet-50-dc5-panoptic
Image Segmentation • 43M • Updated • 34 • 3 -
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
Image Segmentation • Updated • 60.5k • • 39
Collection of image to image editing, image enhancement (SR, deblur, brighten) and text-to-image adapter models.
This collection contains image captioning and OCR models.
-
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 790k • 1.45k -
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 2.63M • 844 -
microsoft/trocr-base-handwritten
Image-to-Text • 0.3B • Updated • 278k • 479 -
microsoft/git-large-coco
Image-to-Text • 0.4B • Updated • 5.33k • 104
Foundation models for computer vision.
Models and applications of OWL-ViT and OWLv2.
A collection of open-source document AI 📄 📝 📈
Papers about vision-language models, most important ones are on top of the list.
-
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 • 11 -
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
Paper • 2404.01331 • Published • 27
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
A comprehensive collection on DAv2
This collection has all the vision language leaderboards.
-
Vidore Leaderboard
🥇199Explore and compare visual document retrieval benchmark results
-
Open VLM Leaderboard
🌎998VLMEvalKit Evaluation Results Collection
-
Vision Arena (Testing VLMs side-by-side)
🖼560Analyze images with multiple vision models for labels and boxes
-
SEED-Bench Leaderboard
🏆85Submit model evaluation results to leaderboard
All the models and demos for SAM2
A collection of real-time detectors.
-
facebook/metaclip-2-worldwide-s16
Zero-Shot Image Classification • 0.4B • Updated • 544 • 8 -
facebook/metaclip-2-worldwide-m16
Zero-Shot Image Classification • 0.5B • Updated • 59 • 3 -
facebook/metaclip-2-worldwide-l14
Zero-Shot Image Classification • 1B • Updated • 149k • 12 -
facebook/metaclip-2-worldwide-b32
Zero-Shot Image Classification • 0.6B • Updated • 96 • 6
All the releases of the week of 30th May.
A collection of DSE models for multimodal retrieval
Models and datasets of the second week of Jan 2025.
Recent depth models
Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone.
-
microsoft/resnet-50
Image Classification • Updated • 195k • • 481 -
google/vit-base-patch16-224-in21k
Image Feature Extraction • 86.4M • Updated • 1.22M • 395 -
google/vit-base-patch32-224-in21k
Image Feature Extraction • 88M • Updated • 5.38k • 19 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 774k • 102
-
facebook/detr-resnet-50
Object Detection • 41.6M • Updated • 418k • • 935 -
facebook/detr-resnet-101-dc5
Object Detection • 60.7M • Updated • 2.85k • 19 -
facebook/detr-resnet-50-dc5
Object Detection • 41.6M • Updated • 2.61k • 6 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145
This is a collection for models that can be used for zero-shot image classification.
-
openai/clip-vit-large-patch14
Zero-Shot Image Classification • 0.4B • Updated • 6.52M • 1.97k -
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 18.9M • 869 -
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
Zero-Shot Image Classification • Updated • 51.2k • 306 -
kakaobrain/align-base
Zero-Shot Image Classification • Updated • 8.71k • 31
-
microsoft/xclip-base-patch32
Video Classification • 0.2B • Updated • 178k • 108 -
facebook/timesformer-base-finetuned-k400
Video Classification • Updated • 85.7k • 42 -
facebook/timesformer-base-finetuned-k600
Video Classification • Updated • 3.61k • 12 -
google/vivit-b-16x2
Video Classification • Updated • 4.99k • 11
This collection contains models and demos of SAM and it's smaller friends.
A collection dedicated to SigLIP applications
-
Draw To Search Art
🐠73Draw/upload image and search among WikiART using SigLIP
-
Compare Clip Siglip
🏃23Compare strong zero-shot image classification models
-
Multilingual Zero Shot Image Clf
🏢13Comparing powerful multilingual zero-shot image clf models
-
BAAI/bunny-phi-2-siglip-lora
Text Generation • Updated • 205 • 48
A collection of everything SegGPT.
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
A collection of video-language models
-
Video Llava
🐨21Generate descriptions by uploading images or videos
-
llava-hf/LLaVA-NeXT-Video-7B-hf
Video-Text-to-Text • 7B • Updated • 93.5k • 122 -
llava-hf/LLaVA-NeXT-Video-7B-DPO-hf
Video-Text-to-Text • 7B • Updated • 1.81k • 11 -
llava-hf/LLaVA-NeXT-Video-7B-32K-hf
Image-Text-to-Text • 8B • Updated • 1.17k • 8
YOLO26 models: detection, segmentation, classification, pose, and OBB variants with demos and ONNX variants.
A collection of real-time detectors.
-
facebook/metaclip-2-worldwide-s16
Zero-Shot Image Classification • 0.4B • Updated • 544 • 8 -
facebook/metaclip-2-worldwide-m16
Zero-Shot Image Classification • 0.5B • Updated • 59 • 3 -
facebook/metaclip-2-worldwide-l14
Zero-Shot Image Classification • 1B • Updated • 149k • 12 -
facebook/metaclip-2-worldwide-b32
Zero-Shot Image Classification • 0.6B • Updated • 96 • 6
All the releases of the week of 30th May.
A collection of DSE models for multimodal retrieval
Models and datasets of the second week of Jan 2025.
-
NVLM: Open Frontier-Class Multimodal LLMs
Paper • 2409.11402 • Published • 74 -
BRAVE: Broadening the visual encoding of vision-language models
Paper • 2404.07204 • Published • 19 -
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Paper • 2403.18814 • Published • 48 -
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 121
Recent depth models
Models mentioned in https://huggingface.co/papers/2404.07204
-
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 774k • 102 -
google/flan-t5-xl
3B • Updated • 207k • 528 -
google/siglip-large-patch16-384
Zero-Shot Image Classification • 0.7B • Updated • 18.1k • 11 -
google/vit-huge-patch14-224-in21k
Image Feature Extraction • 0.6B • Updated • 26.7k • 22
Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone.
-
microsoft/resnet-50
Image Classification • Updated • 195k • • 481 -
google/vit-base-patch16-224-in21k
Image Feature Extraction • 86.4M • Updated • 1.22M • 395 -
google/vit-base-patch32-224-in21k
Image Feature Extraction • 88M • Updated • 5.38k • 19 -
facebook/dinov2-large
Image Feature Extraction • 0.3B • Updated • 774k • 102
-
facebook/deit-base-distilled-patch16-384
Image Classification • 87.6M • Updated • 92.5k • • 7 -
facebook/convnextv2-base-1k-224
Image Classification • 88.7M • Updated • 1.27k • • 4 -
facebook/deit-base-distilled-patch16-224
Image Classification • Updated • 5.28k • • 32 -
google/vit-base-patch32-384
Image Classification • 88.3M • Updated • 4.44k • • 23
-
facebook/detr-resnet-50
Object Detection • 41.6M • Updated • 418k • • 935 -
facebook/detr-resnet-101-dc5
Object Detection • 60.7M • Updated • 2.85k • 19 -
facebook/detr-resnet-50-dc5
Object Detection • 41.6M • Updated • 2.61k • 6 -
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145
A collection of instance/semantic/panoptic segmentation models.
-
facebook/maskformer-swin-large-coco
Image Segmentation • 0.2B • Updated • 472 • 27 -
nvidia/segformer-b0-finetuned-ade-512-512
Image Segmentation • 3.75M • Updated • 606k • • 179 -
facebook/detr-resnet-50-dc5-panoptic
Image Segmentation • 43M • Updated • 34 • 3 -
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
Image Segmentation • Updated • 60.5k • • 39
This is a collection for models that can be used for zero-shot image classification.
-
openai/clip-vit-large-patch14
Zero-Shot Image Classification • 0.4B • Updated • 6.52M • 1.97k -
openai/clip-vit-base-patch32
Zero-Shot Image Classification • Updated • 18.9M • 869 -
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
Zero-Shot Image Classification • Updated • 51.2k • 306 -
kakaobrain/align-base
Zero-Shot Image Classification • Updated • 8.71k • 31
Collection of image to image editing, image enhancement (SR, deblur, brighten) and text-to-image adapter models.
-
microsoft/xclip-base-patch32
Video Classification • 0.2B • Updated • 178k • 108 -
facebook/timesformer-base-finetuned-k400
Video Classification • Updated • 85.7k • 42 -
facebook/timesformer-base-finetuned-k600
Video Classification • Updated • 3.61k • 12 -
google/vivit-b-16x2
Video Classification • Updated • 4.99k • 11
This collection contains image captioning and OCR models.
-
Salesforce/blip-image-captioning-large
Image-to-Text • 0.5B • Updated • 790k • 1.45k -
Salesforce/blip-image-captioning-base
Image-to-Text • Updated • 2.63M • 844 -
microsoft/trocr-base-handwritten
Image-to-Text • 0.3B • Updated • 278k • 479 -
microsoft/git-large-coco
Image-to-Text • 0.4B • Updated • 5.33k • 104
Foundation models for computer vision.
This collection contains models and demos of SAM and it's smaller friends.
Models and applications of OWL-ViT and OWLv2.
A collection dedicated to SigLIP applications
-
Draw To Search Art
🐠73Draw/upload image and search among WikiART using SigLIP
-
Compare Clip Siglip
🏃23Compare strong zero-shot image classification models
-
Multilingual Zero Shot Image Clf
🏢13Comparing powerful multilingual zero-shot image clf models
-
BAAI/bunny-phi-2-siglip-lora
Text Generation • Updated • 205 • 48
A collection of open-source document AI 📄 📝 📈
A collection of everything SegGPT.
Papers about vision-language models, most important ones are on top of the list.
-
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 • 11 -
LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model
Paper • 2404.01331 • Published • 27
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
-
google/owlvit-base-patch32
Zero-Shot Object Detection • 0.2B • Updated • 114k • 145 -
google/owlvit-base-patch16
Zero-Shot Object Detection • Updated • 22.1k • 13 -
google/owlvit-large-patch14
Zero-Shot Object Detection • Updated • 28.5k • 29 -
google/owlv2-base-patch16
Zero-Shot Object Detection • 0.2B • Updated • 365k • 29
A comprehensive collection on DAv2
This collection has all the vision language leaderboards.
-
Vidore Leaderboard
🥇199Explore and compare visual document retrieval benchmark results
-
Open VLM Leaderboard
🌎998VLMEvalKit Evaluation Results Collection
-
Vision Arena (Testing VLMs side-by-side)
🖼560Analyze images with multiple vision models for labels and boxes
-
SEED-Bench Leaderboard
🏆85Submit model evaluation results to leaderboard
A collection of video-language models
-
Video Llava
🐨21Generate descriptions by uploading images or videos
-
llava-hf/LLaVA-NeXT-Video-7B-hf
Video-Text-to-Text • 7B • Updated • 93.5k • 122 -
llava-hf/LLaVA-NeXT-Video-7B-DPO-hf
Video-Text-to-Text • 7B • Updated • 1.81k • 11 -
llava-hf/LLaVA-NeXT-Video-7B-32K-hf
Image-Text-to-Text • 8B • Updated • 1.17k • 8
All the models and demos for SAM2