Yifan Sun

Mr. Yifan Sun

Institute of Geospatial Information, PLA Strategic Support Force Information Engineering University, Zhengzhou, Henan, China
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
10 November 2022 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYifan Sun
Yifan Sun
BLBing Liu
Bing Liu
XYXuchu Yu
Xuchu Yu
AYAnzhu Yu
Anzhu Yu
KGKuiliang Gao
Kuiliang Gao
LDLei Ding
Lei Ding
In recent years, deep-learning-based hyperspectral image (HSI) classification methods have achieved significant development. The superior capability of feature extraction from these data-driven methods dramatically improves the classification performance. However, the previous methods usually require to retrain the network from scratch to obtain the capability of feature extraction adaptive for the target image when facing a new HSI to be classified, which is a time-consuming and redundant process. In this paper, we consider putting this process ahead and making the network have a robust capability of feature extraction with generalization through pre-training. Therefore, the network enables to directly extract features of the target HSI without re-training. For this purpose, we rethink the three-dimension (3D) HSI data from a perspective of spectral sequence, and we attempt to extract the spectral variation information as the spectrum motion feature. Then, we construct an unsupervised spectrum motion feature learning framework (SMF-UL), which can be pre-trained on mass unlabeled HSI data to learn the knowledge about perceiving spectral variation. Furthermore, to achieve the expansion of source data for pre-training, we develop an extendable training dataset construction method, which can integrate HSIs of different sizes, number of bands and sensors into a unified training set to utilize the rapidly growing mass unlabeled HSI data effectively. Finally, we use the trained network to directly extract the spectrum motion feature of the target HSI for classification, so the laborious re-training of the network can be avoided. Extensive experiments show that the proposed SMF-UL acquires the robust capability of feature extraction with generalization through unsupervised learning on mass unlabeled HSI data, and the classification performance of extracted spectrum motion feature is competitive to advanced in-domain and cross-domain methods, which shows its flexibility and superiority. The code of SMF-UL will be open at: https://github.com/sssssyf/SMF-UL.

26 May 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
YSYifan Sun
Yifan Sun
BLBing Liu
Bing Liu
RWRuirui Wang
Ruirui Wang
PZPengqiang Zhang
Pengqiang Zhang
MDMofan Dai
Mofan Dai
In recent years, deep-learning-based hyperspectral image (HSI) classification methods have achieved significant development and gradually become widely applied. The existing advanced methods can achieve near-saturation performance with sufficient labels in a closed-set environment (CSE), i.e., training set and test set are all known categories of ground objects. However, the real world is usually open because of the diversity of land covers, i.e., test-set exists unknown categories that are not labeled in the training set. Therefore, the prevalent advanced CSE methods still cannot effectively and robustly handle unknown categories of ground objects in an open-set environment (OSE). Therefore, we propose a spectral-spatial MLP-like network with reciprocal points learning (SSMLP-RPL) to improve the performance of open-set HSI classification. First, a feature learning framework based on reciprocal points learning (RPL) is constructed to model the extra-category space and reduce the risk of open space. The learned feature space enables to enlarge the distance between the known and unknown categories. Besides, we further propose to utilize a learnable dynamic threshold of each known category to effectively distinguish the unknown categories and improve open performance of the model. Second, to enhance the capacity of feature learning, a spectral-spatial MLP-like network (SSMLP) is designed to capture the spectral-spatial feature merely with a series of fully-connected (FC) layers, which mainly involve SpeFC and SpaFC two modules. Among them, the SpaFC module enables to model spacial semantics, and the SpeFC module enables to model long-distance spectral dependence. Extensive experiments on three benchmark HSIs show that SSMLP-RPL has a competitive performance both in CSE and OSE and even surpasses currently advanced closed-set and open-set HSI classification methods. As an end-to-end HSI classification framework of MLP-backbone, SSMLP network can compete with the advanced works based on CNN and transformer. The code will be open at: https://github.com/sssssyf/SSMLP-RPL.

8 January 2022 in European Journal of Remote Sensing
Verified
Journal Article
Open access
BLBing Liu
Bing Liu
AYAnzhu Yu
Anzhu Yu
KGKuiliang Gao
Kuiliang Gao
XTXiong Tan
Xiong Tan
YSYifan Sun
Yifan Sun
XYXuchu Yu
Xuchu Yu
In recent years, the wide use of deep learning based methods has greatly improved the classification performance of hyperspectral image (HSI). As an effective method to improve the performance of deep convolution networks, attention mechanism is also widely used for HSI classification tasks. However, the majority of the existing attention mechanisms for HSI classification are based on the convolution layer, and the classification accuracy still has margins for improvement. Motivated by the latest self attention mechanism in natural language processing, a deep transformer is proposed for HSI classification in this paper. Specifically, deep transformer along the spectral dimension and the spatial dimension are explored respectively. Then, a deep spatial-spectral transformer (DSS-TRM) is proposed to improve the classification performance of HSI. The contribution of this paper is to make full use of self attention mechanism, that is to use transformer layer instead of convolution layer. More importantly, a DSS-TRM is proposed to realize end-to-end HSI classification. Extensive experiments are conducted on three HSI data sets. The experimental results demonstrates that the proposed DSS-TRM could outperform the traditional convolutional neural networks and attention based methods.

19 March 2022 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
YSYifan Sun
Yifan Sun
BLBing Liu
Bing Liu
XYXuchu Yu
Xuchu Yu
AYAnzhu Yu
Anzhu Yu
ZXZhixiang Xue
Zhixiang Xue
KGKuiliang Gao
Kuiliang Gao
We propose a fully octave convolution network with a pyramid attention mechanism (FOctConvPA) for whole Hyperspectral Image (HSI) classification. Because of the spatial relevance between pixels, effective extraction of global context and long-distance information can help improve the classification performance. However, global information flow is usually accompanied by the loss of local information and details. Therefore, in pursuit of solving this problem effectively, firstly, the proposed method based on the fully convolution network (FCN) uses the whole image as input to reserve original global information, and octave convolution is adopted to reduce spatial computing redundancy and highlight high-frequency edge details. Secondly, the information passes through the encoder and decoder in a resolution lossless form, so the loss of detail can be avoided as far as possible. Thirdly, we utilize the pyramid attention (PA) mechanism to achieve the purpose of global information flowing while long-distance dependencies are captured on both spatial and spectral dimensions. Finally, the mainstream information passing through the decoder is fused with initial information and symmetrical shallow information to improve classification accuracy and restore category boundary and details. Furthermore, to avoid the conflict between limited graphics processing unit (GPU) memory and the randomness of image size, a novel resolution reconstruction classification paradigm is proposed for our network. Experiments on four real benchmark hyperspectral datasets demonstrate that the proposed method could achieve better classification performance compared with other state-of-the-art deep learning models.

12 September 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
BLBing Liu
Bing Liu
YSYifan Sun
Yifan Sun
AYAnzhu Yu
Anzhu Yu
ZXZhixiang Xue
Zhixiang Xue
Zuo XibingZuo Xibing
Zuo Xibing
Hyperspectral image (HSI) classification has always been recognised as a difficult task. It is therefore a research hotspot in remote sensing image processing and analysis, and a number of studies have been conducted to better extract spectral and spatial features. This study aimed to track the variation of the spectrum in hyperspectral images from a sequential data perspective to obtain more distinguishable features. Based on the characteristics of optical flow, this study introduces an optical flow technique for the extraction of spectral flow that denotes the spectral variation and implements a dense optical flow extraction method based on deep matching. Lastly, the extracted spectral flow are combined with the original spectral features and input into a commonly used support vector machine (SVM) classifier to complete the classification. Extensive classification experiments on three benchmark HSI test sets show that the classification accuracy obtained by the spectral flow extracted in this study (SpectralFlow) is higher than traditional spatial feature extraction methods, texture feature extraction methods, and the latest deep-learning-based methods. Furthermore, the proposed method can produce finer classification thematic maps, thereby demonstrating strong practical application potential.

13 October 2022 in Remote Sensing
Verified
Journal Article
Open access
YSYifan Sun
Yifan Sun
BLBing Liu
Bing Liu
XYXuchu Yu
Xuchu Yu
AYAnzhu Yu
Anzhu Yu
KGKuiliang Gao
Kuiliang Gao
LDLei Ding
Lei Ding
Hyperspectral image classification methods based on deep learning have led to remarkable achievements in recent years. However, these methods with outstanding performance are also accompanied by problems such as excessive dependence on the number of samples, poor model generalization, and time-consuming training. Additionally, the previous patch-level feature extraction methods have some limitations, for instance, non-local information is difficult to model, etc. To solve these problems, this paper proposes an image-level feature extraction method with transfer learning. Firstly, we look at a hyperspectral image with hundreds of contiguous spectral bands from a sequential image perspective. We attempt to extract the global spectral variation information between adjacent spectral bands by using the optical flow estimation method. Secondly, we propose an innovative data adaptation strategy to bridge the gap between hyperspectral and video data, and transfer the optical flow estimation network pre-trained with video data to the hyperspectral feature extraction task for the first time. Thirdly, we utilize the traditional classifier to achieve classification. Simultaneously, a vote strategy combined with features at different scales is proposed to improve the classification accuracy further. Extensive, well-designed experiments on four scenes of public hyperspectral images demonstrate that the proposed method (Spe-TL) can obtain results that are competitive with advanced deep learning methods under various sample conditions, with better time effectiveness to adapt to new target tasks. Moreover, it can produce more detailed classification maps that subtly reflect the authentic distribution of ground objects in the original image.