PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets

• URL: http://arxiv.org/abs/2410.10084v2
• Date: Mon, 16 Dec 2024 02:15:53 GMT
• Title: PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets
• Authors: Ali Kashefi,
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks. We introduce PointNet-KAN, which employs KANs instead of traditional networks. We evaluate PointNet-KAN across various degrees and special types such as the Lagrange, Chebyshev, and Gegenbauers.
• Score: 1.90365714903665
• License:
• Abstract: Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks. KANs have been integrated into various deep learning architectures such as convolutional neural networks, graph neural networks, and transformers, with their performance evaluated. However, their effectiveness within point-cloud-based neural networks remains unexplored. To address this gap, we incorporate KANs into PointNet for the first time to evaluate their performance on 3D point cloud classification and segmentation tasks. Specifically, we introduce PointNet-KAN, built upon two key components. First, it employs KANs instead of traditional MLPs. Second, it retains the core principle of PointNet by using shared KAN layers and applying symmetric functions for global feature extraction, ensuring permutation invariance with respect to the input features. In traditional MLPs, the goal is to train the weights and biases with fixed activation functions; however, in KANs, the goal is to train the activation functions themselves. We use Jacobi polynomials to construct the KAN layers. We extensively and systematically evaluate PointNet-KAN across various polynomial degrees and special types such as the Lagrange, Chebyshev, and Gegenbauer polynomials. Our results show that PointNet-KAN achieves competitive performance compared to PointNet with MLPs on benchmark datasets for 3D object classification and segmentation, despite employing a shallower and simpler network architecture. We hope this work serves as a foundation and provides guidance for integrating KANs, as an alternative to MLPs, into more advanced point cloud processing architectures.

Related papers

• Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification [0.0]
  Point-GN is a novel non-parametric network for efficient and accurate 3D point cloud classification. We evaluate Point-GN on two benchmark datasets, ModelNet40 and ScanObjectNN, achieving classification accuracies of 85.29% and 85.89%, respectively.
  arXiv  Detail & Related papers  (2024-12-04T06:20:51Z)
• FreePoint: Unsupervised Point Cloud Instance Segmentation [72.64540130803687]
  We propose FreePoint, for underexplored unsupervised class-agnostic instance segmentation on point clouds. We represent point features by combining coordinates, colors, and self-supervised deep features. Based on the point features, we segment point clouds into coarse instance masks as pseudo labels, which are used to train a point cloud instance segmentation model.
  arXiv  Detail & Related papers  (2023-05-11T16:56:26Z)
• PointPatchMix: Point Cloud Mixing with Patch Scoring [58.58535918705736]
  We propose PointPatchMix, which mixes point clouds at the patch level and generates content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40.
  arXiv  Detail & Related papers  (2023-03-12T14:49:42Z)
• PointResNet: Residual Network for 3D Point Cloud Segmentation and Classification [18.466814193413487]
  Point cloud segmentation and classification are some of the primary tasks in 3D computer vision. In this paper, we propose PointResNet, a residual block-based approach. Our model directly processes the 3D points, using a deep neural network for the segmentation and classification tasks.
  arXiv  Detail & Related papers  (2022-11-20T17:39:48Z)
• PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies [85.14697849950392]
  We revisit the classical PointNet++ through a systematic study of model training and scaling strategies. We propose a set of improved training strategies that significantly improve PointNet++ performance. We introduce an inverted residual bottleneck design and separables into PointNet++ to enable efficient and effective model scaling.
  arXiv  Detail & Related papers  (2022-06-09T17:59:54Z)
• APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification [48.230170172837084]
  Point-cloud-based 3D classification task involves aggregating features from neighbor points. To address these issues, we propose a new local aggregator of linear complexity, coined as APP. We use an online normal estimation module to provide the explainable geometric information to enhance our APP modeling capability.
  arXiv  Detail & Related papers  (2022-05-02T12:21:11Z)
• Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation [12.093182949686781]
  We propose a novel 3D point cloud learning network, referred to as Dynamic Point Feature Aggregation Network (DPFA-Net) DPFA-Net has two variants for semantic segmentation and classification of 3D point clouds. It achieves the state-of-the-art overall accuracy score for semantic segmentation on the S3DIS dataset.
  arXiv  Detail & Related papers  (2021-11-14T05:46:05Z)
• Learning point embedding for 3D data processing [2.12121796606941]
  Current point-based methods are essentially spatial relationship processing networks. Our architecture, PE-Net, learns the representation of point clouds in high-dimensional space. Experiments show that PE-Net achieves the state-of-the-art performance in multiple challenging datasets.
  arXiv  Detail & Related papers  (2021-07-19T00:25:28Z)
• 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)
• SALA: Soft Assignment Local Aggregation for Parameter Efficient 3D Semantic Segmentation [65.96170587706148]
  We focus on designing a point local aggregation function that yields parameter efficient networks for 3D point cloud semantic segmentation. We explore the idea of using learnable neighbor-to-grid soft assignment in grid-based aggregation functions.
  arXiv  Detail & Related papers  (2020-12-29T20:16:37Z)
• SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification [93.54286830844134]
  We propose a method for 3D object completion and classification based on point clouds. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2020-08-17T14:32:35Z)

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.