# GA-NET: Global Attention Network for Point Cloud Semantic Segmentation

arXiv: https://arxiv.org/abs/2107.03101 · HTML: https://mlsanity.com/paper/2107.03101/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)
- [Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark](https://mlsanity.com/paper/1704.03847/) (2017)
- [Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds](https://mlsanity.com/paper/2003.13035/) (2020)
- [PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/1807.00652/) (2018)
- [Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling](https://mlsanity.com/paper/1912.10775/) (2019)
- [LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2006.02706/) (2020)

## Built on by (most cited first, 10 of 10)

- [Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2107.03601/) (2021)
- [Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification](https://mlsanity.com/paper/2207.10278/) (2022)
- [SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation](https://mlsanity.com/paper/2205.13490/) (2022)
- [A Representation Separation Perspective to Correspondences-free Unsupervised 3D Point Cloud Registration](https://mlsanity.com/paper/2203.13239/) (2022)
- [Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey](https://mlsanity.com/paper/2402.12923/) (2024)
- [Searching Dense Point Correspondences via Permutation Matrix Learning](https://mlsanity.com/paper/2210.14897/) (2022)
- [Benchmarking Deep Learning Architectures for Urban Vegetation Point Cloud Semantic Segmentation from MLS](https://mlsanity.com/paper/2306.10274/) (2023)
- [Twin Deformable Point Convolutions for Point Cloud Semantic Segmentation in Remote Sensing Scenes](https://mlsanity.com/paper/2405.19735/) (2024)
- [Towards Semi-supervised Dual-modal Semantic Segmentation](https://mlsanity.com/paper/2409.13325/) (2024)
- [PT-WNO: Point Transformer with Wavelet Neural Operator for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2606.11466/) (2026)

## Abstract (arXiv)

How to learn long-range dependencies from 3D point clouds is a challenging problem in 3D point cloud analysis. Addressing this problem, we propose a global attention network for point cloud semantic segmentation, named as GA-Net, consisting of a point-independent global attention module and a point-dependent global attention module for obtaining contextual information of 3D point clouds in this paper. The point-independent global attention module simply shares a global attention map for all 3D points. In the point-dependent global attention module, for each point, a novel random cross attention block using only two randomly sampled subsets is exploited to learn the contextual information of all the points. Additionally, we design a novel point-adaptive aggregation block to replace linear skip connection for aggregating more discriminate features. Extensive experimental results on three 3D public datasets demonstrate that our method outperforms state-of-the-art methods in most cases.