AGNet: An Attention-Based Graph Network for Point Cloud Classification and Segmentation

Jing, Weipeng; Zhang, Wenjun; Li, Linhui; Di, Donglin; Chen, Guangsheng; Wang, Jian

doi:10.3390/rs14041036

Cited by 31 publications

(14 citation statements)

References 50 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AGNet was proposed [116] by using an attention-based feature extraction module called AGM, which constructs a topology structure in the local region and aggregates the important features using an attention-pooling operation. In this framework, the local feature information is extracted by constructing a topological structure, which facilitates better extracting of the spatial information with different distances.…”

Section: Autonomous Vehiclesmentioning

confidence: 99%

Graph Neural Networks for Intelligent Transportation Systems: A Survey

Rahmani

Baghbani

Bouguila

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Graph neural networks (GNNs) have been extensively used in a wide variety of domains in recent years. Owing to their power in analyzing graph-structured data, they have become broadly popular in intelligent transportation systems (ITS) applications as well. Despite their widespread applications in different transportation domains, there is no comprehensive review of recent advancements and future research directions that covers all transportation areas. Accordingly, in this survey, for the first time, we provide an overview of GNN studies in the general domain of ITS. Unlike previous surveys, which have been limited to traffic forecasting problems, we explore how GNN frameworks have evolved for different ITS applications, including traffic forecasting, demand prediction, autonomous vehicles, intersection management, parking management, urban planning, and transportation safety. Also, we micro-categorize the studies based on their transportation application to identify domainspecific research directions, opportunities, and challenges, which have been missing in previous surveys. Moreover, we identify unique and undiscussed research opportunities and directions, which is the result of reviewing a wide range of transportation applications. The neglected role of edge and graph learning in ITS applications, developing multi-modal models, and exploiting the power of unsupervised and reinforcement learning methods for developing more powerful GNNs are some examples of such new discussions in this survey. Finally, we have identified popular baseline models and datasets in each transportation domain, which facilitate the development and evaluation of future GNNbased frameworks.

show abstract

Section: Autonomous Vehiclesmentioning

confidence: 99%

Graph Neural Networks for Intelligent Transportation Systems: A Survey

Rahmani

Baghbani

Bouguila

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…For example, the pioneered edge-conditional convolution (ECC) [ 24 ] converts the disordered point cloud data into graphs. Jing et al [ 25 ] proposed a novel feature extraction module based on an attention-pooling strategy called the attention graph module (AGM), which constructs a topology structure in the local region and aggregates the important features using the novel and effective attention-pooling operation. The 3DGCN [ 26 ] introduces a learnable 3D kernel structure to guarantee scale invariance and a 3D graph max-pooling operator to obtain more features.…”

Section: Related Workmentioning

confidence: 99%

UFO-Net: A Linear Attention-Based Network for Point Cloud Classification

Guo

Tang

et al. 2023

Sensors

View full text Add to dashboard Cite

Three-dimensional point cloud classification tasks have been a hot topic in recent years. Most existing point cloud processing frameworks lack context-aware features due to the deficiency of sufficient local feature extraction information. Therefore, we designed an augmented sampling and grouping module to efficiently obtain fine-grained features from the original point cloud. In particular, this method strengthens the domain near each centroid and makes reasonable use of the local mean and global standard deviation to extract point cloud’s local and global features. In addition to this, inspired by the transformer structure UFO-ViT in 2D vision tasks, we first tried to use a linearly normalized attention mechanism in point cloud processing tasks, investigating a novel transformer-based point cloud classification architecture UFO-Net. An effective local feature learning module was adopted as a bridging technique to connect different feature extraction modules. Importantly, UFO-Net employs multiple stacked blocks to better capture feature representation of the point cloud. Extensive ablation experiments on public datasets show that this method outperforms other state-of-the-art methods. For instance, our network performed with 93.7% overall accuracy on the ModelNet40 dataset, which is 0.5% higher than PCT. Our network also archived 83.8% overall accuracy on the ScanObjectNN dataset, which is 3.8% better than PCT.

show abstract

“…Compared with PointNet [27] and PointNet++ [28] which are also based on shared MLP, the number of parameters is reduced by a large margin of 72.0% and 34.7%. KCNet [65] 0.9 M -1k points 91.0 PointNet++(SSG) [28] 1.5 M 1684 M 1 k points 90.7 PointNet++(MSG) [28] 1.7 M 4090 M 1 k points 91.9 DGANet [51] 1.7 M -1 k points 92.3 DGCNN [30] 1.8 M 2430 M 1 k points 92.9 GAPointNet [53] 1.9 M 1228 M 1 k points 93.0 AGNet [70] 2.0 M -1 k points 93.4 KD-Net (depth = 15) [19] 2.0 M -32 k points 91.8 SpecGCN [67] 2.0 M 1112 M 1 k points 91.5 PCT [33] 2.9 M 2320 M 1 k points 93.2 PointNet [27] 3.…”

Section: Space and Time Complexity Analysismentioning

confidence: 99%

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

Zheng

Sun

Chen

2022

Sensors

View full text Add to dashboard Cite

Effectively integrating the local features and their spatial distribution information for more effective point cloud analysis is a subject that has been explored for a long time. Inspired by convolutional neural networks (CNNs), this paper studies the relationship between local features and their spatial characteristics and proposes a concise architecture to effectively integrate them instead of designing more sophisticated feature extraction modules. Different positions in the feature map of the 2D image correspond to different weights in the convolution kernel, making the obtained features that are sensitive to local distribution characteristics. Thus, the spatial distribution of the input features of the point cloud within the receptive field is critical for capturing abstract regional aggregated features. We design a lightweight structure to extract local features by explicitly supplementing the distribution information of the input features to obtain distinctive features for point cloud analysis. Compared with the baseline, our model shows improvements in accuracy and convergence speed, and these advantages facilitate the introduction of the snapshot ensemble. Aiming at the shortcomings of the commonly used cosine annealing learning schedule, we design a new annealing schedule that can be flexibly adjusted for the snapshot ensemble technology, which significantly improves the performance by a large margin. Extensive experiments on typical benchmarks verify that, although it adopts the basic shared multi-layer perceptrons (MLPs) as feature extractors, the proposed model with a lightweight structure achieves on-par performance with previous state-of-the-art (SOTA) methods (e.g., MoldeNet40 classification, 0.98 million parameters and 93.5% accuracy; S3DIS segmentation, 1.4 million parameters and 68.7% mIoU).

show abstract

AGNet: An Attention-Based Graph Network for Point Cloud Classification and Segmentation

Cited by 31 publications

References 50 publications

Graph Neural Networks for Intelligent Transportation Systems: A Survey

Graph Neural Networks for Intelligent Transportation Systems: A Survey

UFO-Net: A Linear Attention-Based Network for Point Cloud Classification

A Lightweight Network for Point Cloud Analysis via the Fusion of Local Features and Distribution Characteristics

Contact Info

Product

Resources

About