TL;DR
A domain-aware prompt generation method dubbed DPG is proposed, which is composed of a prompt pre-learning stage and a prompt generator training stage that outperforms other state-of-the-arts DG methods.
Prompt tuning offers an efficient way to adapt frozen vision-language models to unsupervised domain adaptation (UDA). Existing prompt-based UDA methods usually rely on domain-aware prompts, but they often couple category semantics and domain correction throughout the prompt hierarchy. This coupling can introduce redund...
Domain generalization (DG) attempts to generalize a model trained on single or multiple source domains to an unseen target domain. Motivated by the transferability of vision-language pretrained models, we argue that text can provide complementary semantic cues for domain generalization. In this paper, we develop a Text...
Gated Adaptive Prompting (GAP-Prompt) is proposed, a novel method that introduces instance-level adaptability to the prompting process and achieves state-of-the-art performance on fine-grained intra-task diversity.
Prompt engineering has emerged as an effective paradigm for adapting vision-language models (VLMs) to image classification. Although large language models (LLMs) could generate rich visual descriptions, their hallucination often produces inaccurate or weakly discriminative class-specific prompts. Moreover, existing pro...
Considering the difficulty of learning spatially and semantically aware prompt injection, the Hierarchical Prompt Injector is proposed, which enables spatially adaptive prompt injection in foundation models and auxiliary supervision to align hierarchical prompts with their corresponding object regions is introduced.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
