Fan Feng

Mr. Fan Feng

PLA Strategic Support Force Information Engineering University
orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 November 2019 in Sensors
Verified
Journal Article
Open access
PDF file
FFFan Feng
Fan Feng
SWShuangting Wang
Shuangting Wang
CWChunyang Wang
Chunyang Wang
JZJin Zhang
Jin Zhang
Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) provides an ideal solution for feature extraction, and has made remarkable achievements in supervised hyperspectral classification. However, hyperspectral image annotation is time-consuming and laborious, and available training data is usually limited. Due to the “small-sample problem”, CNN-based hyperspectral classification is still challenging. Focused on the limited sample-based hyperspectral classification, we designed an 11-layer CNN model called R-HybridSN (Residual-HybridSN) from the perspective of network optimization. With an organic combination of 3D-2D-CNN, residual learning, and depth-separable convolutions, R-HybridSN can better learn deep hierarchical spatial–spectral features with very few training data. The performance of R-HybridSN is evaluated over three public available hyperspectral datasets on different amounts of training samples. Using only 5%, 1%, and 1% labeled data for training in Indian Pines, Salinas, and University of Pavia, respectively, the classification accuracy of R-HybridSN is 96.46%, 98.25%, 96.59%, respectively, which is far better than the contrast models.

11 September 2020 in Sensors
Verified
Journal Article
Open access
PDF file
JZJin Zhang
Jin Zhang
FWFengyuan Wei
Fengyuan Wei
FFFan Feng
Fan Feng
CWChunyang Wang
Chunyang Wang
Convolutional neural networks provide an ideal solution for hyperspectral image (HSI) classification. However, the classification effect is not satisfactory when limited training samples are available. Focused on “small sample” hyperspectral classification, we proposed a novel 3D-2D-convolutional neural network (CNN) model named AD-HybridSN (Attention-Dense-HybridSN). In our proposed model, a dense block was used to reuse shallow features and aimed at better exploiting hierarchical spatial–spectral features. Subsequent depth separable convolutional layers were used to discriminate the spatial information. Further refinement of spatial–spectral features was realized by the channel attention method and spatial attention method, which were performed behind every 3D convolutional layer and every 2D convolutional layer, respectively. Experiment results indicate that our proposed model can learn more discriminative spatial–spectral features using very few training data. In Indian Pines, Salinas and the University of Pavia, AD-HybridSN obtain 97.02%, 99.59% and 98.32% overall accuracy using only 5%, 1% and 1% labeled data for training, respectively, which are far better than all the contrast models.

21 January 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FFFan Feng
Fan Feng
YZYongsheng Zhang
Yongsheng Zhang
JZJin Zhang
Jin Zhang
BLBing Liu
Bing Liu
Hyperspectral images can capture subtle differences in reflectance of features in hundreds of narrow bands, and its pixel-wise classification is the cornerstone of many applications requiring fine-grained classification results. Although three-dimensional convolutional neural networks (3D-CNN) have been extensively investigated in hyperspectral image classification tasks and have made significant breakthroughs, hyperspectral classification under small sample conditions is still challenging. In order to facilitate small sample hyperspectral classification, a novel mixed spatial-spectral features cascade fusion network (MSSFN) is proposed. First, the covariance structure of hyperspectral data is modeled and dimensionality reduction is conducted using factor analysis. Then, two 3D spatial-spectral residual modules and one 2D separable spatial residual module are used to extract mixed spatial-spectral features. A cascade fusion pattern consisting of intra-block feature fusion and inter-block feature fusion is constructed to enhance the feature extraction capability. Finally, the second-order statistical information of the fused features is mined using second-order pooling and the classification is achieved by the fully connected layer after L2 normalization. On the three public available hyperspectral datasets, Indian Pines, Houston, and University of Pavia, only 5%, 3%, and 1% of the labeled samples were used for training, the accuracy of MSSFN in this paper is 98.52%, 96.31% and 98.83%, respectively, which is far better than the contrast models and verifies the effectiveness of MSSFN in small sample hyperspectral classification tasks.

4 January 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FFFan Feng
Fan Feng
YZYongsheng Zhang
Yongsheng Zhang
JZJin Zhang
Jin Zhang
BLBing Liu
Bing Liu
Hyperspectral images contain rich features in both spectral and spatial domains, which bring opportunities for accurate recognition of similar materials and promote various fine-grained remote sensing applications. Although deep learning models have been extensively investigated in the field of hyperspectral image classification (HSIC) tasks, classification performance is still limited under small sample conditions, and this has been a longstanding problem. The features extracted by complex network structures with large model size are redundant to some extent and prone to overfitting. This paper proposes a low-rank constrained attention-enhanced multiple feature fusion network (LAMFN). Firstly, factor analysis is used to extract very few components that can describe the original data using covariance information to perform spectral feature preprocessing. Then, a lightweight attention-enhanced 3D convolution module is used for deep feature extraction, and the position-sensitive information is supplemented using a 2D coordinate attention. The above widely varying spatial–spectral feature groups are fused through a simple composite residual structure. Finally, low-rank second-order pooling is adopted to enhance the convolutional feature selectivity and achieve classification. Extensive experiments were conducted on four representative hyperspectral datasets with different spatial–spectral characteristics, namely Indian Pines (IP), Pavia Center (PC), Houston (HU), and WHU-HongHu (WHU). The contrast methods include several advanced models proposed recently, including residual CNNs, attention-based CNNs, and transformer-based models. Using only five samples per class for training, LAMFN achieved overall accuracies of 78.15%, 97.18%, 81.35%, and 87.93% on the above datasets, which has an improvement of 0.82%, 1.12%, 1.67%, and 0.89% compared to the second-best model. The running time of LAMFN is moderate. For example, the training time of LAMFN on the WHU dataset was 29.1 s, and the contrast models ranged from 3.0 s to 341.4 s. In addition, ablation experiments and comparisons with some advanced semi-supervised learning methods further validated the effectiveness of the proposed model designs.

1 February 2015 in Optics Communications
Verified
Journal Article
Closed access
BEBo En
Bo En
FDFajie Duan
Fajie Duan
FFFan Feng
Fan Feng
LCLv Chang-Rong
Lv Chang-Rong
FXFu Xiao
Fu Xiao
HTHuang Ting-Ting
Huang Ting-Ting

1 February 2008 in Journal of Systems Engineering and Electronics
Verified
Journal Article
Closed access
LZLi Zhisheng
Li Zhisheng
LJLi Junshan
Li Junshan
FFFan Feng
Fan Feng
XZXin Zhao
Xin Zhao
A self-organizing fuzzy clustering neural network by combining the self-organizing Kohonen clustering network with the fuzzy theory is proposed. This network model is designed for the effectiveness evaluation of electronic countermeasures, which not only exerts the advantages of the fuzzy theory, but also has a good ability in machine learning and data analysis. The subjective value of sample versus class is computed by the fuzzy computing theory, and the classified results obtained by self-organizing learning of Kohonen neural network are represented on output layer. Meanwhile, the fuzzy competition learning algorithm keeps the similar information between samples and overcomes the disadvantages of neural network which has fewer samples. The simulation result indicates that the proposed algorithm is feasible and effective.