Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning them for downstream applications demands substantial computational and storage resources. Parameter-efficient fine-tuning (PEFT) methods offer a promising solution to mitigate these resource requirements, yet most current approaches rely on complex adapter and prompt mechanisms that increase tunable parameters. In this paper, we propose PointLoRA, a simple yet effective method that combines low-rank adaptation (LoRA) with multi-scale token selection to efficiently fine-tune point cloud models. Our approach embeds LoRA layers within the most parameter-intensive components of point cloud transformers, reducing the need for tunable parameters while enhancing global feature capture. Additionally, multi-scale token selection extracts critical local information to serve as prompts for downstream fine-tuning, effectively complementing the global context captured by LoRA. The experimental results across various pre-trained models and three challenging public datasets demonstrate that our approach achieves competitive performance with only 3.43% of the trainable parameters, making it highly effective for resource-constrained applications. Source code is available at:this https URL.
View on arXiv@article{wang2025_2504.16023,
title={ PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning },
author={ Song Wang and Xiaolu Liu and Lingdong Kong and Jianyun Xu and Chunyong Hu and Gongfan Fang and Wentong Li and Jianke Zhu and Xinchao Wang },
journal={arXiv preprint arXiv:2504.16023},
year={ 2025 }
}