TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model

arXiv:2311.18231v2 Announce Type: replace
Abstract: Prompt tuning represents a valuable technique for adapting pre-trained visual-language models (VLM) to various downstream tasks. Recent advancements in CoOp-based methods propose a set of learnable domain-shared or image-conditional textual tokens to facilitate the generation of task-specific textual classifiers. However, those textual tokens have a limited generalization ability regarding unseen domains, as they cannot dynamically adjust to the distribution of testing classes. To tackle this issue, we present a novel Textual-based Class-aware Prompt tuning(TCP) that …

arxiv class cs.cv language language model prompt prompt tuning textual type visual