English

Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning

Computer Vision and Pattern Recognition 2024-12-25 v2

Abstract

As the scale of vision models continues to grow, Visual Prompt Tuning (VPT) has emerged as a parameter-efficient transfer learning technique, noted for its superior performance compared to full fine-tuning. However, indiscriminately applying prompts to every layer without considering their inherent correlations, can cause significant disturbances, leading to suboptimal transferability. Additionally, VPT disrupts the original self-attention structure, affecting the aggregation of visual features, and lacks a mechanism for explicitly mining discriminative visual features, which are crucial for classification. To address these issues, we propose a Semantic Hierarchical Prompt (SHIP) fine-tuning strategy. We adaptively construct semantic hierarchies and use semantic-independent and semantic-shared prompts to learn hierarchical representations. We also integrate attribute prompts and a prompt matching loss to enhance feature discrimination and employ decoupled attention for robustness and reduced inference costs. SHIP significantly improves performance, achieving a 4.9% gain in accuracy over VPT with a ViT-B/16 backbone on VTAB-1k tasks. Our code is available at https://github.com/haoweiz23/SHIP.

Keywords

Cite

@article{arxiv.2412.16956,
  title  = {Semantic Hierarchical Prompt Tuning for Parameter-Efficient Fine-Tuning},
  author = {Haowei Zhu and Fangyuan Zhang and Rui Qin and Tianxiang Pan and Junhai Yong and Bin Wang},
  journal= {arXiv preprint arXiv:2412.16956},
  year   = {2024}
}

Comments

Accepted by ICASSP 2025

R2 v1 2026-06-28T20:45:32.407Z