DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point
Cloud Learning
- URL: http://arxiv.org/abs/2401.02610v2
- Date: Sat, 20 Jan 2024 22:05:39 GMT
- Title: DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point
Cloud Learning
- Authors: Jincen Jiang, Lizhi Zhao, Xuequan Lu, Wei Hu, Imran Razzak, Meili Wang
- Abstract summary: We propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between point parts.
We devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training.
The proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks.
- Score: 23.048005152646592
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent works attempt to extend Graph Convolution Networks (GCNs) to point
clouds for classification and segmentation tasks. These works tend to sample
and group points to create smaller point sets locally and mainly focus on
extracting local features through GCNs, while ignoring the relationship between
point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network
(DHGCN) for explicitly learning the contextual relationships between the
voxelized point parts, which are treated as graph nodes. Motivated by the
intuition that the contextual information between point parts lies in the
pairwise adjacent relationship, which can be depicted by the hop distance of
the graph quantitatively, we devise a novel self-supervised part-level hop
distance reconstruction task and design a novel loss function accordingly to
facilitate training. In addition, we propose the Hop Graph Attention (HGA),
which takes the learned hop distance as input for producing attention weights
to allow edge features to contribute distinctively in aggregation. Eventually,
the proposed DHGCN is a plug-and-play module that is compatible with
point-based backbone networks. Comprehensive experiments on different backbones
and tasks demonstrate that our self-supervised method achieves state-of-the-art
performance. Our source code is available at: https://github.com/Jinec98/DHGCN.
Related papers
- SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks [14.548198408544032]
We treat 3D scene graph alignment as a partial graph-matching problem and propose to solve it with a graph neural network.
We reuse the geometric features learned by a point cloud registration method and associate the clustered point-level geometric features with the node-level semantic feature.
We propose a point-matching rescoring method, that uses the node-wise alignment of the 3D scene graph to reweight the matching candidates from a pre-trained point cloud registration method.
arXiv Detail & Related papers (2024-03-28T15:01:58Z) - Learnable Graph Matching: A Practical Paradigm for Data Association [74.28753343714858]
We propose a general learnable graph matching method to address these issues.
Our method achieves state-of-the-art performance on several MOT datasets.
For image matching, our method outperforms state-of-the-art methods on a popular indoor dataset, ScanNet.
arXiv Detail & Related papers (2023-03-27T17:39:00Z) - Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
Modelling long-range dependencies is critical for scene understanding tasks in computer vision.
A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive.
We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
arXiv Detail & Related papers (2022-09-20T14:41:37Z) - Learning task-specific features for 3D pointcloud graph creation [0.8629912408966145]
We propose a principled way of creating a graph from a 3D pointcloud.
Our method is based on performing k-NN over a transformation of the input 3D pointcloud.
We also introduce a regularization method based on stress minimization, which allows to control how distant is the learnt graph from our baseline: k-NN over xyz space.
arXiv Detail & Related papers (2022-09-02T11:13:02Z) - HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud
Processing [0.7649716717097428]
Motivated by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing.
We propose Hierarchical Point Graph Neural Network (HPGNN)
It learns node features at various levels of graph coarseness to extract information.
This enables to learn over a large point cloud while retaining fine details that existing point-level graph networks struggle to achieve.
arXiv Detail & Related papers (2022-06-05T11:18:09Z) - Graph Attention Networks with Positional Embeddings [7.552100672006174]
Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks.
We propose a framework, termed Graph Attentional Networks with Positional Embeddings (GAT-POS), to enhance GATs with positional embeddings.
We show that GAT-POS reaches remarkable improvement compared to strong GNN baselines and recent structural embedding enhanced GNNs on non-homophilic graphs.
arXiv Detail & Related papers (2021-05-09T22:13:46Z) - One Point is All You Need: Directional Attention Point for Feature
Learning [51.44837108615402]
We present a novel attention-based mechanism for learning enhanced point features for tasks such as point cloud classification and segmentation.
We show that our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks.
arXiv Detail & Related papers (2020-12-11T11:45:39Z) - CatGCN: Graph Convolutional Networks with Categorical Node Features [99.555850712725]
CatGCN is tailored for graph learning when the node features are categorical.
We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification.
arXiv Detail & Related papers (2020-09-11T09:25:17Z) - Sequential Graph Convolutional Network for Active Learning [53.99104862192055]
We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN)
With a small number of randomly sampled images as seed labelled examples, we learn the parameters of the graph to distinguish labelled vs unlabelled nodes.
We exploit these characteristics of GCN to select the unlabelled examples which are sufficiently different from labelled ones.
arXiv Detail & Related papers (2020-06-18T00:55:10Z) - Affinity Graph Supervision for Visual Recognition [35.35959846458965]
We propose a principled method to supervise the learning of weights in affinity graphs.
Our affinity supervision improves relationship recovery between objects, even without manually annotated relationship labels.
We show that affinity learning can also be applied to graphs built from mini-batches, for neural network training.
arXiv Detail & Related papers (2020-03-19T23:52:51Z) - Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature
Interactions [153.6357310444093]
Graph Convolutional Network (GCN) is an emerging technique that performs learning and reasoning on graph data.
We argue that existing designs of GCN forgo modeling cross features, making GCN less effective for tasks or data where cross features are important.
We design a new operator named Cross-feature Graph Convolution, which explicitly models the arbitrary-order cross features with complexity linear to feature dimension and order size.
arXiv Detail & Related papers (2020-03-05T13:05:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.