HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smarter
- URL: http://arxiv.org/abs/2407.05278v3
- Date: Fri, 6 Sep 2024 05:56:39 GMT
- Title: HyperKAN: Kolmogorov-Arnold Networks make Hyperspectral Image Classificators Smarter
- Authors: Valeriy Lobanov, Nikita Firsov, Evgeny Myasnikov, Roman Khabibullin, Artem Nikonorov,
- Abstract summary: We propose the replacement of linear and convolutional layers of traditional networks with KAN-based counterparts.
These modifications allowed us to significantly increase the per-pixel classification accuracy for hyperspectral remote-sensing images.
The greatest effect was achieved for convolutional networks working exclusively on spectral data.
- Score: 0.0699049312989311
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In traditional neural network architectures, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov-Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we propose the replacement of linear and convolutional layers of traditional networks with KAN-based counterparts. These modifications allowed us to significantly increase the per-pixel classification accuracy for hyperspectral remote-sensing images. We modified seven different neural network architectures for hyperspectral image classification and observed a substantial improvement in the classification accuracy across all the networks. The architectures considered in the paper include baseline MLP, state-of-the-art 1D (1DCNN) and 3D convolutional (two different 3DCNN, NM3DCNN), and transformer (SSFTT) architectures, as well as newly proposed M1DCNN. The greatest effect was achieved for convolutional networks working exclusively on spectral data, and the best classification quality was achieved using a KAN-based transformer architecture. All the experiments were conducted using seven openly available hyperspectral datasets. Our code is available at https://github.com/f-neumann77/HyperKAN.
Related papers
- How to Learn More? Exploring Kolmogorov-Arnold Networks for Hyperspectral Image Classification [26.37105279142761]
Kolmogorov-Arnold Networks (KANs) were proposed as viable alternatives for vision transformers (ViTs)
In this study, we assess the effectiveness of KANs for complex hyperspectral image (HSI) data classification.
To enhance the HSI classification accuracy obtained by the KANs, we develop and propose a Hybrid architecture utilizing 1D, 2D, and 3D KANs.
arXiv Detail & Related papers (2024-06-22T03:31:02Z) - CMTNet: Convolutional Meets Transformer Network for Hyperspectral Images Classification [3.821081081400729]
Current convolutional neural networks (CNNs) focus on local features in hyperspectral data.
Transformer framework excels at extracting global features from hyperspectral imagery.
This research introduces the Convolutional Meet Transformer Network (CMTNet)
arXiv Detail & Related papers (2024-06-20T07:56:51Z) - Two-Stream Graph Convolutional Network for Intra-oral Scanner Image
Segmentation [133.02190910009384]
We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes.
Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
arXiv Detail & Related papers (2022-04-19T10:41:09Z) - An Efficient End-to-End 3D Model Reconstruction based on Neural
Architecture Search [5.913946292597174]
We propose an efficient model reconstruction method utilizing neural architecture search (NAS) and binary classification.
Our method achieves significantly higher reconstruction accuracy using fewer network parameters.
arXiv Detail & Related papers (2022-02-27T08:53:43Z) - Learning A 3D-CNN and Transformer Prior for Hyperspectral Image
Super-Resolution [80.93870349019332]
We propose a novel HSISR method that uses Transformer instead of CNN to learn the prior of HSIs.
Specifically, we first use the gradient algorithm to solve the HSISR model, and then use an unfolding network to simulate the iterative solution processes.
arXiv Detail & Related papers (2021-11-27T15:38:57Z) - A Battle of Network Structures: An Empirical Study of CNN, Transformer,
and MLP [121.35904748477421]
Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision.
Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and Vision-Mixer, started to lead new trends.
In this paper, we conduct empirical studies on these DNN structures and try to understand their respective pros and cons.
arXiv Detail & Related papers (2021-08-30T06:09:02Z) - Implementing a foveal-pit inspired filter in a Spiking Convolutional
Neural Network: a preliminary study [0.0]
We have presented a Spiking Convolutional Neural Network (SCNN) that incorporates retinal foveal-pit inspired Difference of Gaussian filters and rank-order encoding.
The model is trained using a variant of the backpropagation algorithm adapted to work with spiking neurons, as implemented in the Nengo library.
The network has achieved up to 90% accuracy, where loss is calculated using the cross-entropy function.
arXiv Detail & Related papers (2021-05-29T15:28:30Z) - Spatial Dependency Networks: Neural Layers for Improved Generative Image
Modeling [79.15521784128102]
We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs)
In our spatial dependency networks (SDNs), feature maps at each level of a deep neural net are computed in a spatially coherent way.
We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation.
arXiv Detail & Related papers (2021-03-16T07:01:08Z) - Spherical Transformer: Adapting Spherical Signal to CNNs [53.18482213611481]
Spherical Transformer can transform spherical signals into vectors that can be directly processed by standard CNNs.
We evaluate our approach on the tasks of spherical MNIST recognition, 3D object classification and omnidirectional image semantic segmentation.
arXiv Detail & Related papers (2021-01-11T12:33:16Z) - Spatio-Temporal Inception Graph Convolutional Networks for
Skeleton-Based Action Recognition [126.51241919472356]
We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition.
Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
arXiv Detail & Related papers (2020-11-26T14:43:04Z)
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.