Generative adversarial networks(GANs)with gaming abilities have been widely applied in image generation.However,gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation...Generative adversarial networks(GANs)with gaming abilities have been widely applied in image generation.However,gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation under varying scenes.Enhancing the relation of hierarchical information in a generation network and enlarging differences of different network architectures can facilitate more structural information to improve the generation effect for image generation.In this paper,we propose an enhanced GAN via improving a generator for image generation(EIGGAN).EIGGAN applies a spatial attention to a generator to extract salient information to enhance the truthfulness of the generated images.Taking into relation the context account,parallel residual operations are fused into a generation network to extract more structural information from the different layers.Finally,a mixed loss function in a GAN is exploited to make a tradeoff between speed and accuracy to generate more realistic images.Experimental results show that the proposed method is superior to popular methods,i.e.,Wasserstein GAN with gradient penalty(WGAN-GP)in terms of many indexes,i.e.,Frechet Inception Distance,Learned Perceptual Image Patch Similarity,Multi-Scale Structural Similarity Index Measure,Kernel Inception Distance,Number of Statistically-Different Bins,Inception Score and some visual images for image generation.展开更多
Dear editor,This letter presents an open-set classification method of remote sensing images(RSIs)based on geometric-spectral reconstruction learning.More specifically,in order to improve the ability of RSI classificat...Dear editor,This letter presents an open-set classification method of remote sensing images(RSIs)based on geometric-spectral reconstruction learning.More specifically,in order to improve the ability of RSI classification model to adapt to the open-set environment,an openset classification method based on geometric and spectral feature fusion is proposed.展开更多
This study proposes a novel gradient‐based neural network model with an activated variable parameter,named as the activated variable parameter gradient‐based neural network(AVPGNN)model,to solve time‐varying constr...This study proposes a novel gradient‐based neural network model with an activated variable parameter,named as the activated variable parameter gradient‐based neural network(AVPGNN)model,to solve time‐varying constrained quadratic programming(TVCQP)problems.Compared with the existing models,the AVPGNN model has the following advantages:(1)avoids the matrix inverse,which can significantly reduce the computing complexity;(2)introduces the time‐derivative of the time‐varying param-eters in the TVCQP problem by adding an activated variable parameter,enabling the AVPGNN model to achieve a predictive calculation that achieves zero residual error in theory;(3)adopts the activation function to accelerate the convergence rate.To solve the TVCQP problem with the AVPGNN model,the TVCQP problem is transformed into a non‐linear equation with a non‐linear compensation problem function based on the Karush Kuhn Tucker conditions.Then,a variable parameter with an activation function is employed to design the AVPGNN model.The accuracy and convergence rate of the AVPGNN model are rigorously analysed in theory.Furthermore,numerical experiments are also executed to demonstrate the effectiveness and superiority of the proposed model.Moreover,to explore the feasibility of the AVPGNN model,appli-cations to the motion planning of a robotic manipulator and the portfolio selection of marketed securities are illustrated.展开更多
基金supported in part by the Science and Technology Development Fund,Macao S.A.R(FDCT)0028/2023/RIA1,in part by Leading Talents in Gusu Innovation and Entrepreneurship Grant ZXL2023170in part by the TCL Science and Technology Innovation Fund under Grant D5140240118in part by the Guangdong Basic and Applied Basic Research Foundation under Grant 2021A1515110079.
文摘Generative adversarial networks(GANs)with gaming abilities have been widely applied in image generation.However,gamistic generators and discriminators may reduce the robustness of the obtained GANs in image generation under varying scenes.Enhancing the relation of hierarchical information in a generation network and enlarging differences of different network architectures can facilitate more structural information to improve the generation effect for image generation.In this paper,we propose an enhanced GAN via improving a generator for image generation(EIGGAN).EIGGAN applies a spatial attention to a generator to extract salient information to enhance the truthfulness of the generated images.Taking into relation the context account,parallel residual operations are fused into a generation network to extract more structural information from the different layers.Finally,a mixed loss function in a GAN is exploited to make a tradeoff between speed and accuracy to generate more realistic images.Experimental results show that the proposed method is superior to popular methods,i.e.,Wasserstein GAN with gradient penalty(WGAN-GP)in terms of many indexes,i.e.,Frechet Inception Distance,Learned Perceptual Image Patch Similarity,Multi-Scale Structural Similarity Index Measure,Kernel Inception Distance,Number of Statistically-Different Bins,Inception Score and some visual images for image generation.
基金supported in part by the National Natural Science Foundation of China(61922029,62101072)the Hunan Provincial Natural Science Foundation of China(2021JJ 30003,2021JJ40570)+2 种基金the Science and Technology Plan Project Fund of Hunan Province(2019RS2016)the Key Research and Development Program of Hunan(2021SK2039)the Scientific Research Foundation of Hunan Education Department(20B022,20B157)。
文摘Dear editor,This letter presents an open-set classification method of remote sensing images(RSIs)based on geometric-spectral reconstruction learning.More specifically,in order to improve the ability of RSI classification model to adapt to the open-set environment,an openset classification method based on geometric and spectral feature fusion is proposed.
基金supported in part by the University of Macao(File No.MYRG2018‐00053‐FST)in part by the Open Research Fund of the Beijing Key Laboratory of Big Data Technology for Food Safety(Project No.BTBD‐2021KF05)in part by the Major Science and Technology Special Project of Yunnan Province(202102AD080006).
文摘This study proposes a novel gradient‐based neural network model with an activated variable parameter,named as the activated variable parameter gradient‐based neural network(AVPGNN)model,to solve time‐varying constrained quadratic programming(TVCQP)problems.Compared with the existing models,the AVPGNN model has the following advantages:(1)avoids the matrix inverse,which can significantly reduce the computing complexity;(2)introduces the time‐derivative of the time‐varying param-eters in the TVCQP problem by adding an activated variable parameter,enabling the AVPGNN model to achieve a predictive calculation that achieves zero residual error in theory;(3)adopts the activation function to accelerate the convergence rate.To solve the TVCQP problem with the AVPGNN model,the TVCQP problem is transformed into a non‐linear equation with a non‐linear compensation problem function based on the Karush Kuhn Tucker conditions.Then,a variable parameter with an activation function is employed to design the AVPGNN model.The accuracy and convergence rate of the AVPGNN model are rigorously analysed in theory.Furthermore,numerical experiments are also executed to demonstrate the effectiveness and superiority of the proposed model.Moreover,to explore the feasibility of the AVPGNN model,appli-cations to the motion planning of a robotic manipulator and the portfolio selection of marketed securities are illustrated.
