Skip to main content

🏢 Bilkent University

ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
·3219 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Segmentation 🏢 Bilkent University
ITACLIP boosts training-free semantic segmentation by architecturally enhancing CLIP, integrating LLM-generated class descriptions, and employing image engineering; achieving state-of-the-art results.