Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis

• URL: http://arxiv.org/abs/2108.09228v1
• Date: Fri, 20 Aug 2021 15:37:13 GMT
• Title: Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis
• Authors: Guoquan Xu, Hezhi Cao, Yifan Zhang, Jianwei Wan, Ke Xu, Yanxin Ma
• Abstract summary: Dual-Neighborhood Deep Fusion Network (DNDFN) is proposed to deal with this problem. DNDFN has two key points. One is combination of local neighborhood and global neigh-borhood. TN-Learning is combined with them to obtain richer neighborhood information. The other is information transfer convolution (IT-Conv) which can learn the structural information between two points and transfer features through it.
• Score: 7.696435157444049
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural network has made remarkable achievements in classification of idealized point cloud, however, non-idealized point cloud classification is still a challenging task. In this paper, DNDFN, namely, Dual-Neighborhood Deep Fusion Network, is proposed to deal with this problem. DNDFN has two key points. One is combination of local neighborhood and global neigh-borhood. nearest neighbor (kNN) or ball query can capture the local neighborhood but ignores long-distance dependencies. A trainable neighborhood learning meth-od called TN-Learning is proposed, which can capture the global neighborhood. TN-Learning is combined with them to obtain richer neighborhood information. The other is information transfer convolution (IT-Conv) which can learn the structural information between two points and transfer features through it. Extensive exper-iments on idealized and non-idealized benchmarks across four tasks verify DNDFN achieves the state of the arts.

Related papers

• VN Network: Embedding Newly Emerging Entities with Virtual Neighbors [59.906332784508706]
  We propose a novel framework, namely Virtual Neighbor (VN) network, to address three key challenges. First, to reduce the neighbor sparsity problem, we introduce the concept of the virtual neighbors inferred by rules. Secondly, we identify both logic and symmetric path rules to capture complex patterns.
  arXiv  Detail & Related papers  (2024-02-21T03:04:34Z)
• Task-Oriented Edge Networks: Decentralized Learning Over Wireless Fronthaul [13.150679121986792]
  This paper studies task-oriented edge networks where multiple edge internet-of-things nodes execute machine learning tasks with the help of powerful deep neural networks (DNNs) at a network cloud.
  arXiv  Detail & Related papers  (2023-12-03T05:24:28Z)
• Point2Vec for Self-Supervised Representation Learning on Point Clouds [66.53955515020053]
  We extend data2vec to the point cloud domain and report encouraging results on several downstream tasks. We propose point2vec, which unleashes the full potential of data2vec-like pre-training on point clouds.
  arXiv  Detail & Related papers  (2023-03-29T10:08:29Z)
• Neural Implicit Dictionary via Mixture-of-Expert Training [111.08941206369508]
  We present a generic INR framework that achieves both data and training efficiency by learning a Neural Implicit Dictionary (NID) Our NID assembles a group of coordinate-based Impworks which are tuned to span the desired function space. Our experiments show that, NID can improve reconstruction of 2D images or 3D scenes by 2 orders of magnitude faster with up to 98% less input data.
  arXiv  Detail & Related papers  (2022-07-08T05:07:19Z)
• FatNet: A Feature-attentive Network for 3D Point Cloud Processing [1.502579291513768]
  We introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings. Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset.
  arXiv  Detail & Related papers  (2021-04-07T23:13:56Z)
• DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network [40.18613107849442]
  Few-shot learning aims to classify images under low-data regimes. Recent work has achieved promising performances by using deep descriptors. We propose a Mutual Nearest Neighbor (MNN) relation to explicitly select the query descriptors that are most relevant to each task.
  arXiv  Detail & Related papers  (2021-03-15T06:57:09Z)
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks [59.378148590027735]
  We propose a graph network layer, known as Node2Seq, to learn node embeddings with explicitly trainable weights for different neighboring nodes. For a target node, our method sorts its neighboring nodes via attention mechanism and then employs 1D convolutional neural networks (CNNs) to enable explicit weights for information aggregation. In addition, we propose to incorporate non-local information for feature learning in an adaptive manner based on the attention scores.
  arXiv  Detail & Related papers  (2021-01-06T03:05:37Z)
• PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [57.49788100647103]
  LiDAR-based 3D object detection is an important task for autonomous driving. Current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
  arXiv  Detail & Related papers  (2020-12-18T18:06:43Z)
• Locality Guided Neural Networks for Explainable Artificial Intelligence [12.435539489388708]
  We propose a novel algorithm for back propagation, called Locality Guided Neural Network(LGNN) LGNN preserves locality between neighbouring neurons within each layer of a deep network. In our experiments, we train various VGG and Wide ResNet (WRN) networks for image classification on CIFAR100.
  arXiv  Detail & Related papers  (2020-07-12T23:45:51Z)
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition [75.4027660840568]
  This paper explores how to enhance the local and global dense feature flow by exploiting hierarchical features fully from all the convolution layers. Technically, we propose an efficient and effective CNN framework, i.e., Fast Dense Residual Network (FDRN) for text recognition.
  arXiv  Detail & Related papers  (2020-01-23T06:55:08Z)

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.