ytaek-oh/fsc-clip
Zero-Shot Image Classification
•
Updated
FSC-CLIP
[EMNLP 2024] Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
-
-
ytaek-oh/cc3m-subset-100k
Viewer • Updated • 102k • 57 -
ytaek-oh/laioncoco-subset-100k
Viewer • Updated • 135k • 53 -
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
Paper • 2410.05210 • Published • 10 -
Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
Paper • 2406.09388 • Published