Hao Shi

Hao Shi

Auto-generated profile, based on publicly available information

Hao Shi

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China

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
17 May 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HSHao Shi
Hao Shi
GCGuo Cao
Guo Cao
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
ZGZixian Ge
Zixian Ge
LYliu yanbo
liu yanbo
Di YangDi Yang
Di Yang
In the hyperspectral image (HSI) classification, there are numerous deep learning-based research routes that have emerged recently. Among them, two methodologies attract our attention. One is CNN-based classification and the other is transformer-based classification. The essence of these two methodologies is to interchange information locally or at a long distance for HSI pixels in the spatial or spectral-spatial domain. There are two principles underlying this essence—the information mixing mechanism and the information mixing domain. Although both CNN-based and transformer-based have made efforts in these two principles and obtained favorable classification results, there is still room for improvement in terms of accuracy and efficiency. To further enhance the accuracy and efficiency under the two principles, fast Fourier transform (FFT) is introduced to HSI classification and a fast Fourier filter is designed to mix information efficiently in the frequency domain by means of FFT. The parametric-free characteristic and fast computation of FFT can assist us in efficiently learning interactions among features in the frequency domain. Furthermore, a fast Fourier filter block is built upon the fast Fourier filter for repeatedly using as a basic block. In addition, we propose a spectral-spatial convolution tokenizer (SSCT) to extract shallow features and prepare spectral-spatial tokens for fast Fourier filter blocks. Finally, by employing SSCT and fast Fourier filter blocks, a novel deep neural network architecture—fast Fourier filter network (F 3 Net) is proposed for HSI classification. F 3 Net-P as a pyramidal variant of F 3 Net is also investigated. Experimental results on four datasets comprehensively evaluate our models and indicate that they are competitive with several current state-of-the-art methods, especially when the training samples are extremely limited. Specifically, F 3 Net-P achieves the highest accuracy of 97.25%, 98.08%, 97.49% and 97.95% on the four datasets, respectively, outperforming second best compared model by 1.49%, 2.03%, 2.14% and 1.94%.

25 December 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HSHao Shi
Hao Shi
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
GCGuo Cao
Guo Cao
Di YangDi Yang
Di Yang
Convolutional neural networks (CNNs) have dominated the hyperspectral image (HSI) classification due to their tremendous feature learning capability. However, the formidable local sensitivity is both a strength and a weakness. Recently, the vision transformers have exhibited impressive performances on various vision problems. Compared with CNNs, they can model long-range dependencies to learn more abundant interactions between spatial locations. Nevertheless, the existing transformer-based HSI classification methods also concentrate too much on the advantages of the transformer architecture and disregard the importance of local dependencies. In addition, token generation and token mixers in transformer-like architectures have not been adequately explored, leading to difficulties in obtaining the best classification performance. To deal with these problems, a novel multiscale hierarchical conv-aided Fourierformer (MHCFormer) is proposed for HSI classification. To the best of our knowledge, this is the first time that CNN, transformer, and Fourier transform are skillfully combined for HSI classification. The proposed MHCFormer involves three stages, i.e., multiscale spectral–spatial token generation, hierarchical token learning, and a classification head. The multiscale spectral–spatial token generation is constructed to transform HSI into tokens with multiscale-enhanced spectral–spatial information. The hierarchical token learning is designed to explore multiscale tokens globally and locally by integrating the design philosophy of transformers and CNNs along with Fourier transforms into a block and stacking the blocks hierarchically. Extensive experimental results on the new WHU-Hi-HanChuan dataset and the widely used Indian Pines and Houston 2013 datasets have demonstrated the superiority of MHCFormer over other state-of-the-art methods. The code of our work will be available publicly at https://github.com/Tikiten/MHCFormer .

6 April 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HSHao Shi
Hao Shi
GCGuo Cao
Guo Cao
ZGZixian Ge
Zixian Ge
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
PFPeng Fu
Peng Fu
Deep-learning methods, especially convolutional neural networks (CNN), have become the first choice for hyperspectral image (HSI) classification to date. It is a common procedure that small cubes are cropped from hyperspectral images and then fed into CNNs. However, standard CNNs find it difficult to extract discriminative spectral–spatial features. How to obtain finer spectral–spatial features to improve the classification performance is now a hot topic of research. In this regard, the attention mechanism, which has achieved excellent performance in other computer vision, holds the exciting prospect. In this paper, we propose a double-branch network consisting of a novel convolution named pyramidal convolution (PyConv) and an iterative attention mechanism. Each branch concentrates on exploiting spectral or spatial features with different PyConvs, supplemented by the attention module for refining the feature map. Experimental results demonstrate that our model can yield competitive performance compared to other state-of-the-art models.

9 April 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
XLXuesong Li
Xuesong Li
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
ZGZixian Ge
Zixian Ge
GCGuo Cao
Guo Cao
HSHao Shi
Hao Shi
PFPeng Fu
Peng Fu
As the hyperspectral images (HSIs) usually have a low spatial resolution, HSI super-resolution has recently attracted more and more attention to enhance the spatial resolution of HSIs. A common method is to fuse the low-resolution (LR) HSI with a multispectral image (MSI) whose spatial resolution is higher than the HSI. In this article, we proposed a novel adaptive nonnegative sparse representation-based model to fuse an HSI and its corresponding MSI. First, basing the linear spectral unmixing, the nonnegative structured sparse representation model estimates the sparse codes of the desired high-resolution HSI from both the LR-HSI and the MSI. Then, the adaptive sparse representation can balance the relationship between the sparsity and collaboration by generating a suitable coefficient. Finally, in order to obtain more accurate results, we alternately optimize the spectral basis and coefficients rather than keeping the spectral basis fixed. The alternating direction method of multipliers is applied to solve the proposed optimization problem. The experimental results on both ground-based HSIs and real remote sensing HSIs show the superiority of our proposed approach to some other state-of-the-art HSI super-resolution methods.

6 May 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
ZGZixian Ge
Zixian Ge
GCGuo Cao
Guo Cao
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
XLXuesong Li
Xuesong Li
HSHao Shi
Hao Shi
PFPeng Fu
Peng Fu
Convolutional neural networks (CNNs), a kind of feedforward neural network with a deep structure, are one of the representative methods in hyperspectral image (HSI) classification. However, redundant information and interclass interference are common and challenging problems in HSI classification. In addition, if the spectral and spatial information is not properly extracted and analyzed, it will affect the classification performance of the network to a great extent. Aiming at these issues, this article proposes an HSI classification method based on an adaptive hash attention mechanism and a lower triangular network (AHA-LT). First, the attention mechanism is introduced in the preprocessing stage, which is composed of the spectral attention module and the adaptive hash spatial attention module in series. Then, the data processed by the attention mechanism are introduced into the lower triangular network (LTNet) to obtain the fused high-dimensional semantic features. Finally, we compress the features and obtain the output classification results through several fully connected layers. Among them, LTNet is composed of 2-D–3-D CNN and multiscale features. The network integrates the characteristics of multibranch, feature fusion, feature compression, and skip connections. Extensive experiments on four widely used HSI data sets show that the proposed method can obtain a great improvement in performance compared with the existing methods.

27 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HSHao Shi
Hao Shi
GCGuo Cao
Guo Cao
Youqiang ZhangYouqiang Zhang
Youqiang Zhang
ZGZixian Ge
Zixian Ge
LYliu yanbo
liu yanbo
PFPeng Fu
Peng Fu
Deep learning (DL) has recently been a core ingredient in modern computer vision tasks, triggering a wave of revolutions in various fields. The hyperspectral image (HSI) classification task is no exception. A wide range of DL-based methods have shone brilliantly in HSI classification. However, understanding how to better exploit spectral and spatial information regarding HSI is still an open area of enquiry. In this article, we propose a hybrid convolution and hybrid resolution network with double attention for HSI classification. First, densely connected 3D convolutional layers are employed to extract preliminary spatial–spectral features. Second, these coarse features are fed to the hybrid resolution module, which mines the features at multiple scales to obtain high-level semantic information and low-level local information. Finally, we introduce a novel attention mechanism for further feature adjustment and refinement. Extensive experiments are conducted to evaluate our model in a holistic manner. Compared to several popular methods, our approach yields promising results for four datasets.