ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
Paper
•
2411.12044
•
Published
•
13
•
2
Mustafa Arda Aydın
aydnarda
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 12 hours ago
Multimodal Autoregressive Pre-training of Large Vision Encoders
commented
a paper
2 days ago
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text,
and Architectural Enhancements
authored
a paper
3 days ago
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text,
and Architectural Enhancements
Organizations
None yet
aydnarda's activity
commented
a
paper
2 days ago