mlsanityData to 7 Oct 2026

S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detection

arXiv 2103.08439 ↗First posted 15 Mar 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D object detection plays a crucial role in environmental perception for autonomous vehicles, which is the prerequisite of decision and control. This paper analyses partition-based methods' inherent drawbacks. In the partition operation, a single instance such as a pedestrian is sliced into several pieces, which we call it the partition effect. We propose the Spatial-Attention Graph Convolution (S-AT GCN), forming the Feature Enhancement (FE) layers to overcome this drawback. The S-AT GCN utilizes the graph convolution and the spatial attention mechanism to extract local geometrical structure features. This allows the network to have more meaningful features for the foreground. Our experiments on the KITTI 3D object and bird's eye view detection show that S-AT Conv and FE layers are effective, especially for small objects. FE layers boost the pedestrian class performance by 3.62% and cyclist class by 4.21% 3D mAP. The time cost of these extra FE layers are limited. PointPillars with FE layers can achieve 48 PFS, satisfying the real-time requirement.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 15 Mar 2021.

Builds on

20 of 33 references.

References · 20

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  6. 2020Point Transformercited by 1,462
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2020PCT: Point cloud transformercited by 730
  9. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  10. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  11. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
8 more
  1. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  2. 2019MVX-Net: Multimodal VoxelNet for 3D Object Detectioncited by 162
  3. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  4. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  5. 2017O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysiscited by 47
  6. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  7. 2019Neural Scene Decomposition for Multi-Person Motion Capturecited by 21
  8. 2018Momen(e)t: Flavor the Moments in Learning to Classify Shapescited by 15

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Boosting 3D Object Detection with Semantic-Aware Multi-Branch Frameworkcited by 1