Heng Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Heng Zhou has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Chunlei Zhang
Beijing Zhongdi Runde Petroleum Technology Company Ltd., Beijing, China
5 shared publications - Ping Zhong
College of Information and Electrical Engineering, China Agricultural University, Beijing, China
3 shared publications - Qiaoyu Ma
College of Information and Electrical Engineering, China Agricultural University, Beijing, China
3 shared publications - Xin Zhang
Department of Statistics and Epidemiology, Graduate School of the PLA General Hospital, Beijing, China
3 shared publications - Yanan Jiang
School of Mathematical Sciences, Beijing Normal University, 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
Latest Publications
- 8 May 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 164
Local-global routing between capsules for hyperspectral image classification with noisy labels
- 8 May 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 164
Local-global routing between capsules for hyperspectral image classification with noisy labels
- 7 April 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 158
Wave-based cross-phase representation for weakly supervised classification
- 7 April 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 158
Wave-based cross-phase representation for weakly supervised classification
- 31 May 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106418
Unsupervised domain adaptation with weak source domain labels via bidirectional subdomain alignment
- 31 May 2024
- Published by Elsevier in Neural Networks
- Vol. 178, 106418
Unsupervised domain adaptation with weak source domain labels via bidirectional subdomain alignment
- Open Access
- 11 March 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 128
SWaveNet: A novel spectral–spatial wave network for hyperspectral image classification- 11 March 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 128
Open AccessSWaveNet: A novel spectral–spatial wave network for hyperspectral image classification - 13 February 2024
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 45 (4) , 1385-1417
Leveraging adaptive spatial shifts multi-layer perceptron with parameterized spatial offsets for hyperspectral image classification
- 13 February 2024
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 45 (4) , 1385-1417
Leveraging adaptive spatial shifts multi-layer perceptron with parameterized spatial offsets for hyperspectral image classification
- Open Access
- 13 September 2023
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 123
A multi-level deformable gated aggregated network for hyperspectral image classification
- 13 September 2023
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 123
Open AccessA multi-level deformable gated aggregated network for hyperspectral image classification
- 29 August 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (22) , 26725-26749
Dictionary cache transformer for hyperspectral image classification
- 29 August 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (22) , 26725-26749
Dictionary cache transformer for hyperspectral image classification
- 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.
- 30 April 2023
- Published by Korean Institute of Smart Media in Korean Institute of Smart Media
- Vol. 12 (3) , 112-119
Size Estimation for Shrimp Using Deep Learning Method
Shrimp farming has been becoming a new source of income for fishermen in South Korea. It is often necessary for fishers to measure the size of the shrimp for the purpose to understand the growth rate of the shrimp and to determine the amount of food put into the breeding pond. Traditional methods rely on humans, which has huge time and labor costs. This paper proposes a deep learning-based method for calculating the size of shrimps automatically. Firstly, we use fine-tuning techniques to update the Mask RCNN model with our farm data, enabling it to segment shrimps and generate shrimp masks. We then use skeletonizing method and maximum inscribed circle to calculate the length and width of shrimp, respectively. Our method is simple yet effective, and most importantly, it requires a small hardware resource and is easy to deploy to shrimp farms.
- 30 April 2023
- Published by Korean Institute of Smart Media in Korean Institute of Smart Media
- Vol. 12 (3) , 112-119
Size Estimation for Shrimp Using Deep Learning Method
Shrimp farming has been becoming a new source of income for fishermen in South Korea. It is often necessary for fishers to measure the size of the shrimp for the purpose to understand the growth rate of the shrimp and to determine the amount of food put into the breeding pond. Traditional methods rely on humans, which has huge time and labor costs. This paper proposes a deep learning-based method for calculating the size of shrimps automatically. Firstly, we use fine-tuning techniques to update the Mask RCNN model with our farm data, enabling it to segment shrimps and generate shrimp masks. We then use skeletonizing method and maximum inscribed circle to calculate the length and width of shrimp, respectively. Our method is simple yet effective, and most importantly, it requires a small hardware resource and is easy to deploy to shrimp farms.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Vision Transformer With Contrastive Learning for Hyperspectral Image Classification
The vision transformer (ViT) has become a hot topic in image processing due to its global feature extraction capabilities. However, the ViT suffers from over-smoothing in feature extraction and over-fitting in the training procedure, so it is hard to achieve satisfactory performance in hyperspectral image (HSI) classification. To address these issues, we propose a ViT with contrastive learning (CViT). The network architecture includes a patch embedding module, transformer blocks, and a classifier. The training of CViT can be considered as an optimization problem with a supervised contrastive loss, an unsupervised contrastive loss, and an ℓ 1 -regularizer with respect to linear self-attention weights. Specifically, the supervised contrastive loss is proposed to alleviate the negative effects of HSI features’ spectral variability and spatial diversity by increasing intra-class consistency. On the other hand, the unsupervised contrastive loss is exploited to reduce redundancy by reconstructing global structural information. In particular, regularized linear self-attention weights reduce the over-smoothing issue. Extensive experimental results on three HSI datasets demonstrate that the proposed CViT achieves competitive performance.
- 10 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Vision Transformer With Contrastive Learning for Hyperspectral Image Classification
The vision transformer (ViT) has become a hot topic in image processing due to its global feature extraction capabilities. However, the ViT suffers from over-smoothing in feature extraction and over-fitting in the training procedure, so it is hard to achieve satisfactory performance in hyperspectral image (HSI) classification. To address these issues, we propose a ViT with contrastive learning (CViT). The network architecture includes a patch embedding module, transformer blocks, and a classifier. The training of CViT can be considered as an optimization problem with a supervised contrastive loss, an unsupervised contrastive loss, and an ℓ 1 -regularizer with respect to linear self-attention weights. Specifically, the supervised contrastive loss is proposed to alleviate the negative effects of HSI features’ spectral variability and spatial diversity by increasing intra-class consistency. On the other hand, the unsupervised contrastive loss is exploited to reduce redundancy by reconstructing global structural information. In particular, regularized linear self-attention weights reduce the over-smoothing issue. Extensive experimental results on three HSI datasets demonstrate that the proposed CViT achieves competitive performance.