Semantic Scholar

LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models

作者：Xu-Cong Wang, Peng-Kun Wang, Zhe Zhao, Li-Heng Yu, Yang Wang

🔗 https://www.semanticscholar.org/paper/3e4ae18e71a25a8ed7ff9df3b997941fd204fa57 ↗

LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models. International Journal of Computer Vision

內容為收集當日抓取的摘要原文。