ITACLIP combines modified CLIP attention, image augmentations, and LLM-generated class descriptions to achieve state-of-the-art training-free semantic segmentation on five benchmarks.
Fossil: Free open-vocabulary semantic seg- mentation through synthetic references retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
ITACLIP combines modified CLIP attention, image augmentations, and LLM-generated class descriptions to achieve state-of-the-art training-free semantic segmentation on five benchmarks.