SS-MLP: A Novel Spectral-Spatial MLP Architecture for Hyperspectral Image Classification

Meng, Zhe; Zhao, Feng; Liang, Miaomiao

doi:10.3390/rs13204060

Cited by 25 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MLP classifier’s structure and ability to handle complex nonlinear features determine its excellent ability. The MLP classifier is composed of three full connection layers, which is more efficient and more suitable for modeling long-range dependencies [ 51 ]. Meanwhile, COPD patients have high heterogeneity and different phenotypes [ 1 ], resulting in complex nonlinear 3D CNN or lung radiomics features extracted from their chest HRCT images.…”

Section: Discussionmentioning

confidence: 99%

Lung Radiomics Features Selection for COPD Stage Classification Based on Auto-Metric Graph Neural Network

et al. 2022

View full text Add to dashboard Cite

Chronic obstructive pulmonary disease (COPD) is a preventable, treatable, progressive chronic disease characterized by persistent airflow limitation. Patients with COPD deserve special consideration regarding treatment in this fragile population for preclinical health management. Therefore, this paper proposes a novel lung radiomics combination vector generated by a generalized linear model (GLM) and Lasso algorithm for COPD stage classification based on an auto-metric graph neural network (AMGNN) with a meta-learning strategy. Firstly, the parenchyma images were segmented from chest high-resolution computed tomography (HRCT) images by ResU-Net. Second, lung radiomics features are extracted from the parenchyma images by PyRadiomics. Third, a novel lung radiomics combination vector (3 + 106) is constructed by the GLM and Lasso algorithm for determining the radiomics risk factors (K = 3) and radiomics node features (d = 106). Last, the COPD stage is classified based on the AMGNN. The results show that compared with the convolutional neural networks and machine learning models, the AMGNN based on constructed novel lung radiomics combination vector performs best, achieving an accuracy of 0.943, precision of 0.946, recall of 0.943, F1-score of 0.943, and ACU of 0.984. Furthermore, it is found that our method is effective for COPD stage classification.

show abstract

Section: Discussionmentioning

confidence: 99%

Lung Radiomics Features Selection for COPD Stage Classification Based on Auto-Metric Graph Neural Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning algorithms have made up for the defects of traditional methods in feature extraction, which has been achieving progress in computer vision tasks, including object detection [20], semantic segmentation [21], and image classification [22]. Furthermore, various deep learning models have been investigated, such as multilayer perceptron (MLP) [23], stacked autoencoder (SAE) [24], and convolutional neural network (CNN) [25]. Feng et al [26] proposed a new adaptive spatial regularization edge SAE which used a super-pixel segmentation method to segment the image into multiple homogeneous regions.…”

Section: Introductionmentioning

confidence: 99%

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Zhang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

Over the past few years, deep learning has been introduced to tackle hyperspectral image (HSI) classification and demonstrated good performance. In particular, the convolutional neural network (CNN) based methods have progressed. However, due to the high dimensionality of HSI and equal treatment of all bands, the performances of CNN based methods are hampered. The labels of land-covers often differ between edge and the center pixels in pixel-centered spatial information. These edge pixels may weaken the discrimination of spatial features and reduce classification accuracy. Motivated by the attention mechanism of the human visual system, the spatial proximity feature selection with residual spatial-spectral attention network is proposed in this article. It contains a residual spatial attention module, a residual spectral attention module, and a spatial proximity feature selection module. The residual spatial attention module aims to select the crucial spatial information, which assigns weights to different features by measuring the similarity between the surrounding elements and their central ones. The residual spectral attention module is designed for spectral bands which are selected from raw input data by emphasizing the valuable bands and suppressing the valueless. According to the spatial distribution of features, the spatial proximity feature selection module is used to filter features effectively. Experiments on three public data sets demonstrate that the proposed network outperforms the state-of-the-art methods in comparison.

show abstract

“…He et al viewed the HSI as a sequence of images and incorporated the spectral information with spatial information via a self-attention mechanism [20]. Meng et al introduced a novel spectral-spatial MLP architecture, which uses matrix transposition and MLPs to capture long-range dependencies and extract more discriminative spectral-spatial features [21]. ViTs and MLP-like models are still preliminarily used for HSI classification and in an early stage of development, which are not as widely used as CNNs.…”

Section: Introductionmentioning

confidence: 99%

Classification of hyperspectral images via improved cycle‐MLP

Gong¹,

Zhang²,

Zhou

et al. 2022

IET Computer Vision

View full text Add to dashboard Cite

Pixel-wise classification of hyperspectral image (HSI) is a hot spot in the field of remote sensing. The classification of HSI requires the model to be more sensitive to dense features, which is quite different from the modelling requirements of traditional image classification tasks. Cycle-Multilayer Perceptron (MLP) has achieved satisfactory results in dense feature prediction tasks because it is an expert in extracting high-resolution features. In order to obtain a more stable receptive field and enhance the effect of feature extraction in multiple directions, we propose an MLP-like model called DriftNet for HSI classification inspired by Cycle-MLP and deformable convolution. Besides, the proposed DriftNet uses a unique ladder-like fully connected structure to achieve progressive activation of neurons and facilitates the fusion of spatial and spectral information, thereby obtaining more sensitive location information for better classification results. Experimental results on three public hyperspectral datasets demonstrate the effectiveness and generalisation of DriftNet. K E Y W O R D S cycleMLP, classification of hyperspectral image, deep learning, driftFCThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

show abstract

SS-MLP: A Novel Spectral-Spatial MLP Architecture for Hyperspectral Image Classification

Cited by 25 publications

References 50 publications

Lung Radiomics Features Selection for COPD Stage Classification Based on Auto-Metric Graph Neural Network

Lung Radiomics Features Selection for COPD Stage Classification Based on Auto-Metric Graph Neural Network

Spatial Proximity Feature Selection With Residual Spatial–Spectral Attention Network for Hyperspectral Image Classification

Classification of hyperspectral images via improved cycle‐MLP

Contact Info

Product

Resources

About