FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
Paper
•
2510.10921
•
Published
•
10
FG-CLIP 2
FG-CLIP 2 is the foundation model for fine-grained vision-language understanding in both English and Chinese.
-
-
qihoo360/fg-clip2-base
Zero-Shot Image Classification • 0.4B • Updated • 4.07k • 21 -
qihoo360/fg-clip2-large
Zero-Shot Image Classification • 0.9B • Updated • 612 • 9 -
qihoo360/fg-clip2-so400m
Zero-Shot Image Classification • 1B • Updated • 400 • 5 -
qihoo360/LIT-CN
Updated • 197 • 1 -
qihoo360/BoxClass-CN
Updated • 98 • 1 -
qihoo360/DOCCI-CN
Viewer • Updated • 5k • 248 • 1 -
qihoo360/DCI-CN
Updated • 374 -
FG CLIP2 Densefeature Demo
🦀1Visualize image similarity to labels
-
FG CLIP2 Retrieval Demo
💻1Classify images based on given labels