Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 5171-5179
DOI: 10.1609/aaai.v38i6.28323 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Yiwen Tang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref).
Abstract (Originalsprache)
The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning (PEFT) techniques are proposed for language and 2D image pre-trained models. However, the specialized PEFT method for 3D pre-trained models is still under-explored. To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks, which consist of a Point-prior Prompt and a Geometry-aware Adapter. The Point-prior Prompt adopts a set of learnable prompt tokens, for which we propose to construct a memory bank with domain-specific knowledge, and utilize a parameter-free attention to enhance the prompt tokens. The Geometry-aware Adapter aims to aggregate point cloud features within spatial neighborhoods to capture fine-grained geometric information through local interactions. Extensive experiments indicate that our Point-PEFT can achieve better performance than the full fine-tuning on various downstream tasks, while using only 5% of the trainable parameters, demonstrating the efficiency and effectiveness of our approach. Code is released at https://github.com/Ivan-Tang-3D/Point-PEFT.
Zitieren
APA
Tang, Y., Zhang, R., Guo, Z., Ma, X., Zhao, B., Wang, Z., Wang, D., & Li, X. (2024). Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 5171-5179. https://doi.org/10.1609/aaai.v38i6.28323
Vancouver
Tang Y, Zhang R, Guo Z, Ma X, Zhao B, Wang Z, et al. Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):5171-5179. doi:10.1609/aaai.v38i6.28323
BibTeX
@article{Tang2024,
author = {Tang, Yiwen and Zhang, Ray and Guo, Zoey and Ma, Xianzheng and Zhao, Bin and Wang, Zhigang and Wang, Dong and Li, Xuelong},
title = {Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {5171--5179},
doi = {10.1609/aaai.v38i6.28323}
}
EUVIMED