Papers › Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

4 Oct 2023arXiv:2310.03059archive 2025-07-28

Yiwen Tang, Ray Zhang, Zoey Guo, Dong Wang, Zhigang Wang, Bin Zhao, Xuelong Li

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

EvenJoker/Point-PEFT officialmentioned in papermentioned on GitHubpytorch report
even-jk/peft-3d officialmentioned in papermentioned on GitHubpytorch report
ivan-tang-3d/peft-3d officialmentioned in papermentioned on GitHubpytorch report
ivan-tang-3d/point-peft officialmentioned in papermentioned on GitHubpytorch report
ivan-tang-3d/any2point mentioned on GitHubpytorch report
ivan-tang-3d/viewrefer3d mentioned on GitHubpytorch report
ziyuguo99/viewrefer3d mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

parameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adapter

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections