arXiv subjects

Xuyang Li

Publications and source records attributed to Xuyang Li.

27 records · Page 2Linked to original sources

arXiv2024

SpectralGPT: Spectral Remote Sensing Foundation Model

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS big data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS big data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.

cs.CV↗

arXiv2023

UAV Obstacle Avoidance by Human-in-the-Loop Reinforcement in Arbitrary 3D Environment

This paper focuses on the continuous control of the unmanned aerial vehicle (UAV) based on a deep reinforcement learning method for a large-scale 3D complex environment. The purpose is to make the UAV reach any target point from a certain starting point, and the flying height and speed are variable during navigation. In this work, we propose a deep reinforcement learning (DRL)-based method combined with human-in-the-loop, which allows the UAV to avoid obstacles automatically during flying. We design multiple reward functions based on the relevant domain knowledge to guide UAV navigation. The role of human-in-the-loop is to dynamically change the reward function of the UAV in different situations to suit the obstacle avoidance of the UAV better. We verify the success rate and average step size on urban, rural, and forest scenarios, and the experimental results show that the proposed method can reduce the training convergence time and improve the efficiency and accuracy of navigation tasks. The code is available on the website https://github.com/Monnalo/UAV_navigation.

cs.RO↗

arXiv2023

Rethinking the editing of generative adversarial networks: a method to estimate editing vectors based on dimension reduction

While Generative Adversarial Networks (GANs) have recently found applications in image editing, most previous GAN-based image editing methods require largescale datasets with semantic segmentation annotations for training, only provide high level control, or merely interpolate between different images. Previous researchers have proposed EditGAN for high-quality, high-precision semantic image editing with limited semantic annotations by finding `editing vectors'. However, it is noticed that there are many features that are not highly associated with semantics, and EditGAN may fail on them. Based on the orthogonality of latent space observed by EditGAN, we propose a method to estimate editing vectors that do not rely on semantic segmentation nor differentiable feature estimation network. Our method assumes that there is a correlation between the intensity distribution of features and the distribution of hidden vectors, and estimates the relationship between the above distributions by sampling the feature intensity of the image corresponding to several hidden vectors. We modified Linear Discriminant Analysis (LDA) to deal with both binary feature editing and continuous feature editing. We then found that this method has a good effect in processing features such as clothing type and texture, skin color and hair.

cs.CV↗

arXiv2023

Low-Carbon Economic Dispatch of Bulk Power Systems Using Nash Bargaining Game

Decarbonization of power systems plays a crucial role in achieving carbon neutral goals across the globe, but there exists a sharp contradiction between the emission reduction and levelized generation cost. Therefore, it is of great importance for power system operators to take economic as well as low-carbon factors into account. This paper establishes a low-carbon economic dispatch model of bulk power systems based on Nash bargaining game, which derives a Nash bargaining solution making a reasonable trade-off between economic and low-carbon objectives. Because the Nash bargaining solution satisfies Pareto effectiveness, we analyze the computational complexity of Pareto frontiers with parametric linear programming and interpret the inefficiency of the method. Instead, we assign a group of dynamic weights in the objective function of the proposed low-carbon economic dispatch model so as to improve the computational efficiency by decoupling time periods and avoiding the complete computation of Pareto frontiers. In the end, we validate the proposed model and the algorithm by a realistic nationwide simulation in mainland China.

eess.SY↗

arXiv2022

Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components

Structural components are typically exposed to dynamic loading, such as earthquakes, wind, and explosions. Structural engineers should be able to conduct real-time analysis in the aftermath or during extreme disaster events requiring immediate corrections to avoid fatal failures. As a result, it is crucial to predict dynamic stress distributions during highly disruptive events in real-time. Currently available high-fidelity methods, such as Finite Element Models (FEMs), suffer from their inherent high complexity and are computationally prohibitive. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, Neuro-DynaStress, is proposed to predict the entire sequence of stress distribution based on finite element simulations using a partial differential equation (PDE) solver. The model was designed and trained to use the geometry, boundary conditions and sequence of loads as input and predict the sequences of high-resolution stress contours. The performance of the proposed framework is compared to finite element simulations using a PDE solver.

physics.geo-ph↗

arXiv2022

Physics Informed Neural Network for Dynamic Stress Prediction

Structural failures are often caused by catastrophic events such as earthquakes and winds. As a result, it is crucial to predict dynamic stress distributions during highly disruptive events in real time. Currently available high-fidelity methods, such as Finite Element Models (FEMs), suffer from their inherent high complexity. Therefore, to reduce computational cost while maintaining accuracy, a Physics Informed Neural Network (PINN), PINN-Stress model, is proposed to predict the entire sequence of stress distribution based on Finite Element simulations using a partial differential equation (PDE) solver. Using automatic differentiation, we embed a PDE into a deep neural network's loss function to incorporate information from measurements and PDEs. The PINN-Stress model can predict the sequence of stress distribution in almost real-time and can generalize better than the model without PINN.

cs.LG↗

arXiv2022

NeuralSI: Structural Parameter Identification in Nonlinear Dynamical Systems

Structural monitoring for complex built environments often suffers from mismatch between design, laboratory testing, and actual built parameters. Additionally, real-world structural identification problems encounter many challenges. For example, the lack of accurate baseline models, high dimensionality, and complex multivariate partial differential equations (PDEs) pose significant difficulties in training and learning conventional data-driven algorithms. This paper explores a new framework, dubbed NeuralSI, for structural identification by augmenting PDEs that govern structural dynamics with neural networks. Our approach seeks to estimate nonlinear parameters from governing equations. We consider the vibration of nonlinear beams with two unknown parameters, one that represents geometric and material variations, and another that captures energy losses in the system mainly through damping. The data for parameter estimation is obtained from a limited set of measurements, which is conducive to applications in structural health monitoring where the exact state of an existing structure is typically unknown and only a limited amount of data samples can be collected in the field. The trained model can also be extrapolated under both standard and extreme conditions using the identified structural parameters. We compare with pure data-driven Neural Networks and other classical Physics-Informed Neural Networks (PINNs). Our approach reduces both interpolation and extrapolation errors in displacement distribution by two to five orders of magnitude over the baselines. Code is available at https://github.com/human-analysis/neural-structural-identification

cs.LG↗

arXiv2021

Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization

The widely-used cross-entropy (CE) loss-based deep networks achieved significant progress w.r.t. the classification accuracy. However, the CE loss can essentially ignore the risk of misclassification which is usually measured by the distance between the prediction and label in a semantic hierarchical tree. In this paper, we propose to incorporate the risk-aware inter-class correlation in a discrete optimal transport (DOT) training framework by configuring its ground distance matrix. The ground distance matrix can be pre-defined following a priori of hierarchical semantic risk. Specifically, we define the tree induced error (TIE) on a hierarchical semantic tree and extend it to its increasing function from the optimization perspective. The semantic similarity in each level of a tree is integrated with the information gain. We achieve promising results on several large scale image classification tasks with a semantic tree structure in a plug and play manner.

cs.CV↗

arXiv2021

A new communication paradigm: from bit accuracy to semantic fidelity

Wireless communication has achieved great success in the past several decades. The challenge is of improving bandwidth with limited spectrum and power consumption, which however has gradually become a bottleneck with evolution going on. The intrinsic problem is that communication is modeled as a message transportation from sender to receiver and pursues for an exact message replication in Shannon's information theory, which certainly leads to large bandwidth and power requirements with data explosion. However, the goal for communication among intelligent agents, entities with intelligence including humans, is to understand the meaning or semantics underlying data, not an accurate recovery of the transmitted messages. The separate first transmission and then understanding is a waste on bandwidth. In this article, we deploy semantics to solve the spectrum and power bottleneck and propose a first understanding and then transmission framework with high semantic fidelity. We first give a brief introduction of semantics covering the definition and properties to show the insights and scope of this paper. Then the proposed communication towards semantic fidelity framework is introduced, which takes the above mentioned properties into account to further improve efficiency. Specially, a semantic transformation is introduced to transform the input into semantic symbols. Different from the conventional transformations in signal processing area, for example discrete cosine transform, the transformation is with data loss, which is also the reason that the proposed framework can achieve large bandwidth saving with high semantic fidelity. Besides, we also discuss semantic noise and performance measurement. To evaluate the effectiveness, a case study of audio transmission is carried out. Finally, we discuss the typical applications and open challenges.

cs.NI↗