Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large vision transformers to downstream tasks without the prohibitive computational costs of full fine-tuning. While existing visual prompt tuning (VPT) methods have made significant strides, they predominantly rely on static, domain-specific prompts that fail to capture the rich visual diversity within individual instances. This paper introduces VAPT (Visual Variational Autoencoder Prompt Tuning), a novel framework that generates dynamic, input-dependent prompts using a variational autoencoder architecture. By learning a latent representation of image-specific features and decoding them into customized prompts, VAPT adapts to the unique visual characteristics of each input. Extensive experiments on FGVC, HTA, and VTAB-1k benchmarks demonstrate that our approach consistently outperforms state-of-the-art PEFT methods. Notably, VAPT achieves +3.2\% improvement over VPT-Deep on HTA, with an average performance gain of +2.0\% across all three datasets.
View on arXiv@article{xiao2025_2503.17650,
title={ Visual Variational Autoencoder Prompt Tuning },
author={ Xi Xiao and Yunbei Zhang and Yanshuh Li and Xingjian Li and Tianyang Wang and Jihun Hamm and Xiao Wang and Min Xu },
journal={arXiv preprint arXiv:2503.17650},
year={ 2025 }
}