Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification

• URL: http://arxiv.org/abs/2504.15155v1
• Date: Mon, 21 Apr 2025 14:57:48 GMT
• Title: Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification
• Authors: Guandong Li, Mengxia Ye,
• Abstract summary: KANet is an improved 3D-DenseNet model, consisting of 3D KAN Conv and an adaptive grid update mechanism.<n> KANet enhances model representation capability through a 3D dynamic expert convolution system without increasing network depth or width.<n>The proposed method demonstrates superior performance on IN, UP, and KSC datasets, outperforming mainstream hyperspectral image classification approaches.
• Score: 12.168520751389622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks face several challenges in hyperspectral image classification, including high-dimensional data, sparse distribution of ground objects, and spectral redundancy, which often lead to classification overfitting and limited generalization capability. To more efficiently adapt to ground object distributions while extracting image features without introducing excessive parameters and skipping redundant information, this paper proposes KANet based on an improved 3D-DenseNet model, consisting of 3D KAN Conv and an adaptive grid update mechanism. By introducing learnable univariate B-spline functions on network edges, specifically by flattening three-dimensional neighborhoods into vectors and applying B-spline-parameterized nonlinear activation functions to replace the fixed linear weights of traditional 3D convolutional kernels, we precisely capture complex spectral-spatial nonlinear relationships in hyperspectral data. Simultaneously, through a dynamic grid adjustment mechanism, we adaptively update the grid point positions of B-splines based on the statistical characteristics of input data, optimizing the resolution of spline functions to match the non-uniform distribution of spectral features, significantly improving the model's accuracy in high-dimensional data modeling and parameter efficiency, effectively alleviating the curse of dimensionality. This characteristic demonstrates superior neural scaling laws compared to traditional convolutional neural networks and reduces overfitting risks in small-sample and high-noise scenarios. KANet enhances model representation capability through a 3D dynamic expert convolution system without increasing network depth or width. The proposed method demonstrates superior performance on IN, UP, and KSC datasets, outperforming mainstream hyperspectral image classification approaches.

Related papers

• Expert Kernel Generation Network Driven by Contextual Mapping for Hyperspectral Image Classification [12.168520751389622]
  Deep neural networks face several challenges in hyperspectral image classification, including high-dimensional data, sparse distribution of ground objects, and spectral redundancy.<n>This paper proposes EKGNet based on an improved 3D-DenseNet model, consisting of a context-aware mapping network and a dynamic kernel generation module.<n>The proposed method demonstrates superior performance on IN, UP, and KSC datasets, outperforming mainstream hyperspectral image classification approaches.
  arXiv  Detail & Related papers  (2025-04-17T16:00:06Z)
• 3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image Classification [12.168520751389622]
  Deep neural networks face numerous challenges in hyperspectral image classification.<n>This paper proposes WCNet, an improved 3D-DenseNet model integrated with wavelet transforms.<n> Experimental results demonstrate superior performance on the IN, UP, and KSC datasets.
  arXiv  Detail & Related papers  (2025-04-15T01:39:42Z)
• Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification [12.168520751389622]
  Deep neural networks face several challenges in hyperspectral image classification.<n>These include complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features.<n>This paper proposes a Spatial-Geometry Enhanced 3D Dynamic Snake Network (SG-DSCNet) based on an improved 3D-DenseNet model.
  arXiv  Detail & Related papers  (2025-04-06T12:21:39Z)
• Efficient Dynamic Attention 3D Convolution for Hyperspectral Image Classification [12.168520751389622]
  This paper proposes a dynamic attention convolution design based on an improved 3D-DenseNet model.<n>The design employs multiple parallel convolutional kernels instead of a single kernel and assigns dynamic attention weights to these parallel convolutions.<n>The proposed method demonstrates superior performance in both inference speed and accuracy, outperforming mainstream hyperspectral image classification methods on the IN, UP, and KSC datasets.
  arXiv  Detail & Related papers  (2025-03-30T15:12:23Z)
• Hyperspectral Images Efficient Spatial and Spectral non-Linear Model with Bidirectional Feature Learning [7.06787067270941]
  We propose a novel framework that significantly reduces data volume while enhancing classification accuracy.<n>Our model employs a bidirectional reversed convolutional neural network (CNN) to efficiently extract spectral features, complemented by a specialized block for spatial feature analysis.
  arXiv  Detail & Related papers  (2024-11-29T23:32:26Z)
• Geometric Algebra Planes: Convex Implicit Neural Volumes [70.12234371845445]
  We show that GA-Planes is equivalent to a sparse low-rank factor plus low-resolution matrix. We also show that GA-Planes can be adapted for many existing representations.
  arXiv  Detail & Related papers  (2024-11-20T18:21:58Z)
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• Learned Vertex Descent: A New Direction for 3D Human Model Fitting [64.04726230507258]
  We propose a novel optimization-based paradigm for 3D human model fitting on images and scans. Our approach is able to capture the underlying body of clothed people with very different body shapes, achieving a significant improvement compared to state-of-the-art. LVD is also applicable to 3D model fitting of humans and hands, for which we show a significant improvement to the SOTA with a much simpler and faster method.
  arXiv  Detail & Related papers  (2022-05-12T17:55:51Z)
• FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism [49.89268018642999]
  We propose a fast shape-based network (FS-Net) with efficient category-level feature extraction for 6D pose estimation. The proposed method achieves state-of-the-art performance in both category- and instance-level 6D object pose estimation.
  arXiv  Detail & Related papers  (2021-03-12T03:07:24Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)
• Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution [82.1739023587565]
  We propose a novel spectral-spatial residual network for hyperspectral image super-resolution (SSRNet) Our method can effectively explore spatial-spectral information by using 3D convolution instead of 2D convolution, which enables the network to better extract potential information. In each unit, we employ spatial and temporal separable 3D convolution to extract spatial and spectral information, which not only reduces unaffordable memory usage and high computational cost, but also makes the network easier to train.
  arXiv  Detail & Related papers  (2020-01-14T03:34:55Z)

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.