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 V2APT (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, V2APT 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, V2APT achieves +3.2\% improvement over VPT-Deep on HTA, with an average performance gain of +2.0\% across all three datasets.
@article{arxiv.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}
}