Eduardo Pacheco’s Post

View profile for Eduardo Pacheco, graphic

Member of Technical Staff @ Argmax, Inc.

🤗 ❤️ (Grounding) 🦕 Yesterday the famous Grounding DINO model landed on Hugging Face transformers main branch! You're now just one pip install away. Grounding DINO is a Zero-Shot object detection model, thus it's not constrained to a closed set of labels and can detect a wide range of objects. The model was released last year and got quite attention for its capabilities and possible combos with other models like Segment Anything (SAM). I've created a simple Demo to let you try the model look at the links below. Checkpoints: https://lnkd.in/dyFGBGk3 GroundingDINO Demo: https://lnkd.in/dfT9MQrt

  • No alternative text description for this image
👋 Luca Baggi

AI Engineer @xtream • Maintainer @functime.ai • Machine Learning and Statistics @UniMi

5mo

What's the difference between SAM and DINO?

Yacine Lamari

Étudiant en Master 2 Data Science

5mo

Are the features extracted from an image using Dino or grounding Dino the same, or has there been a modification made to the architecture?

Caleb Fedyshen

Full Stack Software Guy @ HyprPixl | Prev. Data Developer Intern @ Suncor

5mo

I prefer “hotdog” and “not hotdog”

Piotr Skalski

Open Source Lead @ Roboflow | Computer Vision | Vision Language Models

5mo

That’s a great news! I was waiting for GroundingDINO in transformers!

Milad Farzalizadeh

Machine Learning & Computer Vision Engineer @ TVCONAL | Sports Analytics

5mo

Great job Eduardo Pacheco. Will it be possible to fine tune the Grounding DINO using Huggingface interface?

Naif A.

Machine Learning Engineer | Graduate Research Assistant @ ASU Biodesign Institute

5mo

Eduardo Pacheco Interesting !! Could this automatically auto annotate hundreds or thousands of similar images ? And the annotations be saved and formatted for a Model like YOLOv9 ?

Thanks for the huge work! Cant wait to try

Biswanath Saha

PhD Student @ Kyushu University, Fukuoka, Japan | MEXT Scholar | Building large-scale image processing pipelines for microscopy | Data analyst | Photographer | Foodie

5mo

we can finetune the model now, more easily I guess.

Dr. Anca-Roxana Tudoran

Principal Software Engineer

5mo

Anisat Aydieva

See more comments

To view or add a comment, sign in

Explore topics