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

• URL: http://arxiv.org/abs/2410.10084v1
• Date: Mon, 14 Oct 2024 01:57:06 GMT
• Title: PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets
• Authors: Ali Kashefi,
• Abstract summary: We introduce PointNet-KAN, a neural network for 3D point cloud classification and segmentation tasks. It employs Kolmogorov-Arnold Networks (KANs) instead of traditional Multilayer Perceptrons (MLPs)
• Score: 1.90365714903665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce PointNet-KAN, a neural network for 3D point cloud classification and segmentation tasks, built upon two key components. First, it employs Kolmogorov-Arnold Networks (KANs) instead of traditional Multilayer Perceptrons (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 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

• Kolmogorov-Arnold PointNet: Deep learning for prediction of fluid fields on irregular geometries [1.90365714903665]
  We present a novel supervised deep learning framework for the prediction of incompressible steady-state fluid flow fields in irregular domains. In KA-PointNet, we implement shared Kolmogorov-Arnold Networks (KANs) in the segmentation branch of the PointNet architecture. We compare the performance of PointNet with shared KANs (i.e., KA-PointNet) and PointNet with shared Multilayer Perceptrons (MLPs)
  arXiv  Detail & Related papers  (2024-08-06T04:28:16Z)
• Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis [59.12922158979068]
  Recently-based methods have shown strong performance in point cloud analysis. Simple architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. We propose Point Deformable Network (PDNet) to capture long-range relations with strong representation ability.
  arXiv  Detail & Related papers  (2023-12-20T14:52:07Z)
• 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)
• Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework [55.40001810884942]
  We introduce a pure residual network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark.
  arXiv  Detail & Related papers  (2022-02-15T01:39:07Z)
• 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)
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation [111.7241018610573]
  We present PointGroup, a new end-to-end bottom-up architecture for instance segmentation. We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid. A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength. We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best
  arXiv  Detail & Related papers  (2020-04-03T16:26:37Z)

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.