Papers › Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space

Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space

8 Mar 2023arXiv:2303.04599archive 2025-07-28

Yahui Liu, Bin Tian, Yisheng Lv, Lingxi Li, FeiYue Wang

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention, but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space (content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an Inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectNN. Source code of this paper is available at https://github.com/yahuiliu99/PointConT.

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

yahuiliu99/pointcont 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 Point Cloud Classification Classification Clustering Point Cloud Classification Supervised Only 3D Point Cloud Classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Point Cloud Classification	ModelNet40	PointConT	Overall Accuracy	93.5	#58 of 111	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	PointConT	Mean Accuracy	88.5	#18 of 77	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	PointConT	Overall Accuracy	90.3	#18 of 77	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	PointConT (no voting)	Mean Accuracy	86.0	#41 of 77	Archive leaderboard	report
3D Point Cloud Classification	ScanObjectNN	PointConT (no voting)	Overall Accuracy	88.0	#41 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 Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer fail

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