Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models

Autor:	Fu, Shuai, Wang, Xiequn, Huang, Qiushi, Zhang, Yu
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent properties of learnable soft-prompt vectors, specifically the impact of their norms to the performance of VLMs. This motivates us to pose an unexplored research question: ``Do we need to normalize the soft prompts in VLMs?'' To fill this research gap, we first uncover a phenomenon, called the \textbf{Low-Norm Effect} by performing extensive corruption experiments, suggesting that reducing the norms of certain learned prompts occasionally enhances the performance of VLMs, while increasing them often degrades it. To harness this effect, we propose a novel method named \textbf{N}ormalizing th\textbf{e} soft-pro\textbf{m}pt v\textbf{e}ctors of vi\textbf{si}on-language model\textbf{s} (\textbf{Nemesis}) to normalize soft-prompt vectors in VLMs. To the best of our knowledge, our work is the first to systematically investigate the role of norms of soft-prompt vector in VLMs, offering valuable insights for future research in soft-prompt tuning. The code is available at \texttt{\href{https://github.com/ShyFoo/Nemesis}{https://github.com/ShyFoo/Nemesis}}. Comment: Accepted at ICLR 2024 (Spotlight)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2408.13979 Zobrazit plný text záznamu View this record from Arxiv