🚀🚀Introducing Ferret, a new MLLM that can refer and ground anything anywhere at any granularity. 📰https://t.co/gED9Vu0I4y1⃣ Ferret enables referring of an image region at any shape2⃣ It often shows better precise understanding of small image regions than GPT-4V (sec 5.6) pic.twitter.com/yVzgVYJmHc— Zhe Gan (@zhegan4) October 12, 2023
🚀🚀Introducing Ferret, a new MLLM that can refer and ground anything anywhere at any granularity. 📰https://t.co/gED9Vu0I4y1⃣ Ferret enables referring of an image region at any shape2⃣ It often shows better precise understanding of small image regions than GPT-4V (sec 5.6) pic.twitter.com/yVzgVYJmHc