Yuanxi Peng
YOU?
Author Swipe
View article: EDTST: Efficient Dynamic Token Selection Transformer for Hyperspectral Image Classification
EDTST: Efficient Dynamic Token Selection Transformer for Hyperspectral Image Classification Open
Hyperspectral images, characterized by rich spectral information, enable precise pixel-level classification and are thus widely employed in remote sensing applications. Although convolutional neural networks (CNNs) have demonstrated effect…
View article: ATIS-Driven 3DCNet: A Novel Three-Stream Hyperspectral Fusion Framework with Knowledge from Downstream Classification Performance
ATIS-Driven 3DCNet: A Novel Three-Stream Hyperspectral Fusion Framework with Knowledge from Downstream Classification Performance Open
Reconstructing high-resolution hyperspectral images (HR-HSIs) by fusing low-resolution hyperspectral images (LR-HSIs) and high-resolution multispectral images (HR-MSIs) is a significant challenge in image processing. Traditional fusion met…
View article: G&G Attack: General and Geometry-Aware Adversarial Attack on the Point Cloud
G&G Attack: General and Geometry-Aware Adversarial Attack on the Point Cloud Open
Deep neural networks have been shown to produce incorrect predictions when imperceptible perturbations are introduced into the clean input. This phenomenon has garnered significant attention and extensive research in 2D images. However, re…
View article: BinaryViT: Binary Vision Transformer for Hyperspectral Image Classification
BinaryViT: Binary Vision Transformer for Hyperspectral Image Classification Open
Vision transformers have demonstrated remarkable performance in hyperspectral image classification tasks. However, their complex computational mechanisms and excessive parameterization severely restrict deployment on resource-constrained p…
View article: Asymmetric Network Based on Feedback and Transformer for Multispectral LiDAR Point Cloud Semantic Segmentation
Asymmetric Network Based on Feedback and Transformer for Multispectral LiDAR Point Cloud Semantic Segmentation Open
The 3-D point cloud semantic segmentation extends the development of computer vision. Accurate point cloud semantic segmentation is a fundamental problem in point cloud applications. However, effective point cloud semantic segmentation is …
View article: Different-Mode Power Splitters for Optical Testing of Three-Channel and Dual-Mode Waveguide Crossing
Different-Mode Power Splitters for Optical Testing of Three-Channel and Dual-Mode Waveguide Crossing Open
We study that the different-mode (waveguide-connected) power splitter [(W)PS] can provide different-mode testing points for the optical testing. With the PS or WPS providing two different-mode testing points, the measured insertion losses …
View article: Enhancing Regular Expression Processing through Field-Programmable Gate Array-Based Multi-Character Non-Deterministic Finite Automata
Enhancing Regular Expression Processing through Field-Programmable Gate Array-Based Multi-Character Non-Deterministic Finite Automata Open
This work investigates the advantages of FPGA-based Multi-Character Non-Deterministic Finite Automata (MC-NFA) for enhancing regular expression processing over traditional software-based methods. By integrating Field-Programmable Gate Arra…
View article: Equal Emphasis on Data and Network: A Two-Stage 3D Point Cloud Object Detection Algorithm with Feature Alignment
Equal Emphasis on Data and Network: A Two-Stage 3D Point Cloud Object Detection Algorithm with Feature Alignment Open
Three-dimensional object detection is a pivotal research topic in computer vision, aiming to identify and locate objects in three-dimensional space. It has wide applications in various fields such as geoscience, autonomous driving, and dro…
View article: A Novel Database Acceleration Technology for Full Table Scans
A Novel Database Acceleration Technology for Full Table Scans Open
Advancements in hardware technology, especially Field Programmable Gate Arrays (FPGAs), have shown potential in enhancing database performance. Yet, much of the existing research has neglected crucial aspects such as the database-hardware …
View article: Boundary-Aware Deformable Spiking Neural Network for Hyperspectral Image Classification
Boundary-Aware Deformable Spiking Neural Network for Hyperspectral Image Classification Open
A few spiking neural network (SNN)-based classifiers have been proposed for hyperspectral images (HSI) classification to alleviate the higher computational energy cost problem. Nevertheless, due to the lack of ability to distinguish bounda…
View article: Inverse-designed ultra-compact multi-channel and multi-mode waveguide crossings
Inverse-designed ultra-compact multi-channel and multi-mode waveguide crossings Open
In this work, we use the inverse design method to design three-channel and four-channel dual-mode waveguide crossings with the design regions of 4.32 µm-wide regular hexagon and 6.68 µm-wide regular octagon, respectively. Based on the high…
View article: Different-mode power splitters based on a multi-dimension direct-binary-search algorithm
Different-mode power splitters based on a multi-dimension direct-binary-search algorithm Open
In this work, we design, fabricate, and characterize a different-mode (waveguide-connected) power splitter ((W)PS) by what we believe to be a novel multi-dimension direct-binary-search algorithm that can significantly balance the device pe…
View article: Correlation Matrix-Based Fusion of Hyperspectral and Multispectral Images
Correlation Matrix-Based Fusion of Hyperspectral and Multispectral Images Open
The fusion of the hyperspectral image (HSI) and the multispectral image (MSI) is commonly employed to obtain a high spatial resolution hyperspectral image (HR-HSI); however, existing methods often involve complex feature extraction and opt…
View article: Three-dimensional mode-division multiplexing system
Three-dimensional mode-division multiplexing system Open
Blindly increasing the channels of the mode (de)multiplexer on the single-layer chip can cause the device structure to be too complex to optimize. The three-dimensional (3D) mode division multiplexing (MDM) technology is a potential soluti…
View article: Psychiatric disorders associated with immune checkpoint inhibitors: a pharmacovigilance analysis of the FDA Adverse Event Reporting System (FAERS) database
Psychiatric disorders associated with immune checkpoint inhibitors: a pharmacovigilance analysis of the FDA Adverse Event Reporting System (FAERS) database Open
View article: A Method for Calculating the Derivative of Activation Functions Based on Piecewise Linear Approximation
A Method for Calculating the Derivative of Activation Functions Based on Piecewise Linear Approximation Open
Nonlinear functions are widely used as activation functions in artificial neural networks, which have a great impact on the fitting ability of artificial neural networks. Due to the complexity of the activation function, the computation of…
View article: Romat: Role-Based Multi-Agent Transformer for Generalizable Heterogeneous Cooperation
Romat: Role-Based Multi-Agent Transformer for Generalizable Heterogeneous Cooperation Open
View article: Multispectral LiDAR Point Cloud Segmentation for Land Cover Leveraging Semantic Fusion in Deep Learning Network
Multispectral LiDAR Point Cloud Segmentation for Land Cover Leveraging Semantic Fusion in Deep Learning Network Open
Multispectral LiDAR technology can simultaneously acquire spatial geometric data and multispectral wavelength intensity information, which can provide richer attribute features for semantic segmentation of point cloud scenes. However, due …
View article: Hyperspectral Multispectral Image Fusion via Fast Matrix Truncated Singular Value Decomposition
Hyperspectral Multispectral Image Fusion via Fast Matrix Truncated Singular Value Decomposition Open
Recently, methods for obtaining a high spatial resolution hyperspectral image (HR-HSI) by fusing a low spatial resolution hyperspectral image (LR-HSI) and high spatial resolution multispectral image (HR-MSI) have become increasingly popula…
View article: PointSwin: Modeling Self-Attention with Shifted Window on Point Cloud
PointSwin: Modeling Self-Attention with Shifted Window on Point Cloud Open
As a pioneering work that directly applies deep learning methods to raw point cloud data, PointNet has the advantages of fast convergence speed and high computational efficiency. However, its feature learning in local areas has a certain d…
View article: Adaptive Linearization for the Sub-Nyquist Photonic Receiver Based on Deep Learning
Adaptive Linearization for the Sub-Nyquist Photonic Receiver Based on Deep Learning Open
Due to the nonlinear and aliasing effects, the sub-Nyquist photonic receiver for radio frequency (RF) signals with large instantaneous bandwidth suffers limited dynamic range and noise performance. We designated a deep residual network (Re…
View article: Introducing Improved Transformer to Land Cover Classification Using Multispectral LiDAR Point Clouds
Introducing Improved Transformer to Land Cover Classification Using Multispectral LiDAR Point Clouds Open
The use of Transformer-based networks has been proposed for the processing of general point clouds. However, there has been little research related to multispectral LiDAR point clouds that contain both spatial coordinate information and mu…
View article: CAEVT: Convolutional Autoencoder Meets Lightweight Vision Transformer for Hyperspectral Image Classification
CAEVT: Convolutional Autoencoder Meets Lightweight Vision Transformer for Hyperspectral Image Classification Open
Convolutional neural networks (CNNs) have been prominent in most hyperspectral image (HSI) processing applications due to their advantages in extracting local information. Despite their success, the locality of the convolutional layers wit…
View article: A Two-Staged Feature Extraction Method Based on Total Variation for Hyperspectral Images
A Two-Staged Feature Extraction Method Based on Total Variation for Hyperspectral Images Open
Effective feature extraction (FE) has always been the focus of hyperspectral images (HSIs). For aerial remote-sensing HSIs processing and its land cover classification, in this article, an efficient two-staged hyperspectral FE method based…
View article: Deep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning
Deep Spatial-Spectral Subspace Clustering for Hyperspectral Images Based on Contrastive Learning Open
Hyperspectral image (HSI) clustering is a major challenge due to the redundant spectral information in HSIs. In this paper, we propose a novel deep subspace clustering method that extracts spatial–spectral features via contrastive learning…
View article: Blind Fusion of Hyperspectral Multispectral Images Based on Matrix Factorization
Blind Fusion of Hyperspectral Multispectral Images Based on Matrix Factorization Open
The fusion of low spatial resolution hyperspectral images and high spatial resolution multispectral images in the same scenario is important for the super-resolution of hyperspectral images. The spectral response function (SRF) and the poi…
View article: Contrastive Learning Based on Transformer for Hyperspectral Image Classification
Contrastive Learning Based on Transformer for Hyperspectral Image Classification Open
Recently, deep learning has achieved breakthroughs in hyperspectral image (HSI) classification. Deep-learning-based classifiers require a large number of labeled samples for training to provide excellent performance. However, the availabil…
View article: Fast and Stable Hyperspectral Multispectral Image Fusion Technique Using Moore–Penrose Inverse Solver
Fast and Stable Hyperspectral Multispectral Image Fusion Technique Using Moore–Penrose Inverse Solver Open
Fusion low-resolution hyperspectral images (LR-HSI) and high-resolution multispectral images (HR-MSI) are important methods for obtaining high-resolution hyperspectral images (HR-HSI). Some hyperspectral image fusion application areas have…
View article: A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification
A Lightweight 1-D Convolution Augmented Transformer with Metric Learning for Hyperspectral Image Classification Open
Hyperspectral image (HSI) classification is the subject of intense research in remote sensing. The tremendous success of deep learning in computer vision has recently sparked the interest in applying deep learning in hyperspectral image cl…
View article: Hyperspectral Open Set Classification towards Deep Networks Based on Boxplot
Hyperspectral Open Set Classification towards Deep Networks Based on Boxplot Open
Recently, hyperspectral imaging (HSI) supervised classification has achieved an astonishing performance by using deep learning. However, most of them take the ideal assumption of ‘closed set’, where all testing classes have been known duri…