# Rethinking Attention Module Design for Point Cloud Analysis

arXiv: https://arxiv.org/abs/2407.19294 · HTML: https://mlsanity.com/paper/2407.19294/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 61 references that are in the map.
- First posted on arXiv 27 Jul 2024.

## Builds on (most cited first, 30 of 53)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://mlsanity.com/paper/2111.14819/) (2021)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Rethinking and Improving Relative Position Encoding for Vision Transformer](https://mlsanity.com/paper/2107.14222/) (2021)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [MVTN: Multi-View Transformation Network for 3D Shape Recognition](https://mlsanity.com/paper/2011.13244/) (2020)
- [Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network](https://mlsanity.com/paper/1811.02565/) (2018)
- [A Closer Look at Local Aggregation Operators in Point Cloud Analysis](https://mlsanity.com/paper/2007.01294/) (2020)
- [Associatively Segmenting Instances and Semantics in Point Clouds](https://mlsanity.com/paper/1902.09852/) (2019)
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://mlsanity.com/paper/2207.10315/) (2022)

## Built on by (most cited first, 2 of 2)

- [SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity](https://mlsanity.com/paper/2504.19581/) (2025)
- [Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels](https://mlsanity.com/paper/2510.09035/) (2025)

## Abstract (arXiv)

In recent years, there have been significant advancements in applying attention mechanisms to point cloud analysis. However, attention module variants featured in various research papers often operate under diverse settings and tasks, incorporating potential training strategies. This heterogeneity poses challenges in establishing a fair comparison among these attention module variants. In this paper, we address this issue by rethinking and exploring attention module design within a consistent base framework and settings. Both global-based and local-based attention methods are studied, with a focus on the selection basis and scales of neighbors for local-based attention. Different combinations of aggregated local features and computation methods for attention scores are evaluated, ranging from the initial addition/concatenation-based approach to the widely adopted dot product-based method and the recently proposed vector attention technique. Various position encoding methods are also investigated. Our extensive experimental analysis reveals that there is no universally optimal design across diverse point cloud tasks. Instead, drawing from best practices, we propose tailored attention modules for specific tasks, leading to superior performance on point cloud classification and segmentation benchmarks.