Kai Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kai Zhang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Chunlei Zhang
Beijing Zhongdi Runde Petroleum Technology Company Ltd., Beijing, China
3 shared publications - Zitong Zhang
State Key Laboratory of Petroleum Resources and Engineering, China University of Petroleum (Beijing), Beijing, China
3 shared publications - Heng Zhou
College of Information and Electrical Engineering, China Agricultural University, Beijing, China
2 shared publications - Yanan Jiang
School of Mathematical Sciences, Beijing Normal University, Beijing, China
2 shared publications - Jianxi Huang1 shared publication
Jigang Tong
1 shared publication
Latest Publications
- 20 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 349
DNesTMamba: A Deformable Nested Transformer with Integrated Mamba for hyperspectral image classification
- 20 June 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 349
DNesTMamba: A Deformable Nested Transformer with Integrated Mamba for hyperspectral image classification
- 21 April 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 121
EEG-ConvMamba: Motor imagery EEG decoding and visualization via convolutional neural networks and Mamba⋆
- 21 April 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 121
EEG-ConvMamba: Motor imagery EEG decoding and visualization via convolutional neural networks and Mamba⋆
- Open Access
- 12 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 17207-17220
LDS2MLP: A Novel Learnable Dilated Spectral-Spatial MLP for Hyperspectral Image Classification
The Multilayer Perceptron (MLP) has gained widespread popularity and demonstrated outstanding performance in hyperspectral image (HSI) classification in recent years. However, the native MLP architecture and its variants are insufficient in expressing fine spatial structural information and long-range dependencies. To this end, a Learnable Dilated Spectral-Spatial MLP (LDS $^{2}$ MLP) is proposed for HSI classification. LDS $^{2}$ MLP applies the learnable dilated receptive field and grouped MLP to extract more discriminative spectral-spatial features with fewer computational costs, which improves the classification performance. Specifically, a plug-and-play Spectral-Spatial Mixing (S $^{2}$ Mixing) block is designed to aggregate grouped spectral detail information and fine spatial structural features. The S $^{2}$ Mixing block consists of two feature extraction modules operating on the spectral and spatial domains. The Spectral Grouping Mixer (SeG Mixer) module captures subtle spectral differences through grouped MLP. The Spatial Dilating with Learnable Spacing Mixer (SaDLS Mixer) module employs a dilated receptive field with learnable spacing to enhance the refined expression of spatial structural features. Extensive experiments on four public HSI datasets illustrate that the proposed LDS $^{2}$ MLP outperforms state-of-the-art deep learning models in classification performance. Additionally, the proposed model is shown to be efficient and generalizable in HSI classification with limited samples.
- 12 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 17207-17220
Open AccessLDS2MLP: A Novel Learnable Dilated Spectral-Spatial MLP for Hyperspectral Image Classification
The Multilayer Perceptron (MLP) has gained widespread popularity and demonstrated outstanding performance in hyperspectral image (HSI) classification in recent years. However, the native MLP architecture and its variants are insufficient in expressing fine spatial structural information and long-range dependencies. To this end, a Learnable Dilated Spectral-Spatial MLP (LDS $^{2}$ MLP) is proposed for HSI classification. LDS $^{2}$ MLP applies the learnable dilated receptive field and grouped MLP to extract more discriminative spectral-spatial features with fewer computational costs, which improves the classification performance. Specifically, a plug-and-play Spectral-Spatial Mixing (S $^{2}$ Mixing) block is designed to aggregate grouped spectral detail information and fine spatial structural features. The S $^{2}$ Mixing block consists of two feature extraction modules operating on the spectral and spatial domains. The Spectral Grouping Mixer (SeG Mixer) module captures subtle spectral differences through grouped MLP. The Spatial Dilating with Learnable Spacing Mixer (SaDLS Mixer) module employs a dilated receptive field with learnable spacing to enhance the refined expression of spatial structural features. Extensive experiments on four public HSI datasets illustrate that the proposed LDS $^{2}$ MLP outperforms state-of-the-art deep learning models in classification performance. Additionally, the proposed model is shown to be efficient and generalizable in HSI classification with limited samples.
- Open Access
- 25 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 7135-7150
SMoINet: Spectral–Spatial Multiorder Interactions Network for Hyperspectral Image Classification
Deep learning methods have shown great promise in automatically extracting features from hyperspectral images (HSI) for classification purposes. Recently, researchers have recognized the importance of high-order feature interactions-capturing relationships between features in different image regions-in extracting discriminative features. Despite their effectiveness, existing deep learning models for HSI classification often overlook high-order feature interactions, resulting in suboptimal performance. To address this issue, we propose a novel spectral-spatial multi-order interaction network (S $^{2}$ MoINet) for HSI classification. The proposed framework can effectively extract highly discriminative features by leveraging correlations between features in different locations, significantly improving the classification accuracy. More specifically, we design a multi-order spectral-spatial interaction block in the framework to extract the high-order and generalized features by leveraging the interaction between spatial and spectral features. Based on experimental results from four public HSI datasets, it has been shown that the proposed S $^{2}$ MoINet delivers optimal classification results when compared to other state-of-the-art methods.
- 25 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 16 (19391404) , 7135-7150
Open AccessSMoINet: Spectral–Spatial Multiorder Interactions Network for Hyperspectral Image Classification
Deep learning methods have shown great promise in automatically extracting features from hyperspectral images (HSI) for classification purposes. Recently, researchers have recognized the importance of high-order feature interactions-capturing relationships between features in different image regions-in extracting discriminative features. Despite their effectiveness, existing deep learning models for HSI classification often overlook high-order feature interactions, resulting in suboptimal performance. To address this issue, we propose a novel spectral-spatial multi-order interaction network (S $^{2}$ MoINet) for HSI classification. The proposed framework can effectively extract highly discriminative features by leveraging correlations between features in different locations, significantly improving the classification accuracy. More specifically, we design a multi-order spectral-spatial interaction block in the framework to extract the high-order and generalized features by leveraging the interaction between spatial and spectral features. Based on experimental results from four public HSI datasets, it has been shown that the proposed S $^{2}$ MoINet delivers optimal classification results when compared to other state-of-the-art methods.
- Open Access
- 12 April 2022
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 16 (5) , 468-478
Classification of hyperspectral images via improved cycle‐MLP
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.
- 12 April 2022
- Published by Institution of Engineering and Technology (IET) in IET Computer Vision
- Vol. 16 (5) , 468-478
Open AccessClassification of hyperspectral images via improved cycle‐MLP
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.