Papers › Positional Prompt Tuning for Efficient 3D Representation Learning

Positional Prompt Tuning for Efficient 3D Representation Learning

21 Aug 2024arXiv:2408.11567archive 2025-07-28

Shaochen Zhang, Zekun Qi, Runpei Dong, Xiuxiu Bai, Xing Wei

Point cloud analysis has achieved significant development and is well-performed in multiple downstream tasks like point cloud classification and segmentation, etc. Being conscious of the simplicity of the position encoding structure in Transformer-based architectures, we attach importance to the position encoding as a high-dimensional part and the patch encoder to offer multi-scale information. Together with the sequential Transformer, the whole module with position encoding comprehensively constructs a multi-scale feature abstraction module that considers both the local parts from the patch and the global parts from center points as position encoding. With only a few parameters, the position embedding module fits the setting of PEFT (Parameter-Efficient Fine-Tuning) tasks pretty well. Thus we unfreeze these parameters as a fine-tuning part. At the same time, we review the existing prompt and adapter tuning methods, proposing a fresh way of prompts and synthesizing them with adapters as dynamic adjustments. Our Proposed method of PEFT tasks, namely PPT, with only 1.05% of parameters for training, gets state-of-the-art results in several mainstream datasets, such as 95.01% accuracy in the ScanObjectNN OBJ_BG dataset. Codes will be released at https://github.com/zsc000722/PPT.

Paper PDF Code

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

Code

zsc000722/ppt officialmentioned in papermentioned 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

3D Parameter-Efficient Fine-Tuning for Classification 3D Point Cloud Classification Point Cloud Classification Representation Learning parameter-efficient fine-tuning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Point Cloud Classification	ModelNet40	PointMAE+PPT	Overall Accuracy	93.88	#38 of 111	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	ReCon+PPT	OBJ-BG (OA)	95.01	#23 of 77	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	ReCon+PPT	OBJ-ONLY (OA)	93.28	#23 of 77	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	ReCon+PPT	Overall Accuracy	89.52	#23 of 77	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Adapter Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

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