针对现有生成对抗网络的单图像超分辨率重建在大尺度因子下存在训练不稳定、特征提取不足和重建结果纹理细节严重缺失的问题,提出一种拆分注意力网络的单图超分辨率重建方法。首先,以拆分注意力残差模块作为基本残差块构造生成器,提高...针对现有生成对抗网络的单图像超分辨率重建在大尺度因子下存在训练不稳定、特征提取不足和重建结果纹理细节严重缺失的问题,提出一种拆分注意力网络的单图超分辨率重建方法。首先,以拆分注意力残差模块作为基本残差块构造生成器,提高生成器特征提取的能力。其次,在损失函数中引入鲁棒性更好的Charbonnier损失函数和Focal Frequency Loss损失函数代替均方差损失函数,同时加入正则化损失平滑训练结果,防止图像过于像素化。最后,在生成器和判别器中采用谱归一化处理,提高网络的稳定性。在4倍放大因子下,与其他方法在Set5、Set14、BSDS100、Urban100测试集上进行测试比较,本文方法的峰值信噪比比其他对比方法的平均值提升1.419 dB,结构相似性比其他对比方法的平均值提升0.051。实验数据和效果图表明,该方法主观上具有丰富的细节和更好的视觉效果,客观上具有较高的峰值信噪比值和结构相似度值。展开更多
Multiple complex networks, each with different properties and mutually fused, have the problems that the evolving process is time varying and non-equilibrium, network structures are layered and interlacing, and evolvi...Multiple complex networks, each with different properties and mutually fused, have the problems that the evolving process is time varying and non-equilibrium, network structures are layered and interlacing, and evolving characteristics are difficult to be measured. On that account, a dynamic evolving model of complex network with fusion nodes and overlap edges（CNFNOEs） is proposed. Firstly, we define some related concepts of CNFNOEs, and analyze the conversion process of fusion relationship and hierarchy relationship. According to the property difference of various nodes and edges, fusion nodes and overlap edges are subsequently split, and then the CNFNOEs is transformed to interlacing layered complex networks（ILCN）. Secondly,the node degree saturation and attraction factors are defined. On that basis, the evolution algorithm and the local world evolution model for ILCN are put forward. Moreover, four typical situations of nodes evolution are discussed, and the degree distribution law during evolution is analyzed by means of the mean field method.Numerical simulation results show that nodes unreached degree saturation follow the exponential distribution with an error of no more than 6%; nodes reached degree saturation follow the distribution of their connection capacities with an error of no more than 3%; network weaving coefficients have a positive correlation with the highest probability of new node and initial number of connected edges. The results have verified the feasibility and effectiveness of the model, which provides a new idea and method for exploring CNFNOE＇s evolving process and law. Also, the model has good application prospects in structure and dynamics research of transportation network, communication network, social contact network,etc.展开更多
如何提取多尺度特征和建模远程通道间的语义依赖仍是表情识别网络面临的挑战。本文提出一种基于金字塔分割注意力的残差网络(Residual network based on pyramid split attention, PSA-ResNet)模型,该模型将ResNet50残差模块中的3×...如何提取多尺度特征和建模远程通道间的语义依赖仍是表情识别网络面临的挑战。本文提出一种基于金字塔分割注意力的残差网络(Residual network based on pyramid split attention, PSA-ResNet)模型,该模型将ResNet50残差模块中的3×3卷积替换成金字塔分割注意力,以有效提取多尺度特征,增强跨通道语义信息的相关性。同时,为缩小同类表情之间的差异,扩大不同类表情之间的距离,在训练过程中引入了Softmax loss和Center loss联合损失函数优化模型参数。本文所提出的方法在Fer2013和CK+两个公开的数据集上进行仿真实验,分别取得了74.26%和98.35%的准确率,进一步证实了该方法相比前沿算法具有更好的表情识别效果。展开更多
文摘针对现有生成对抗网络的单图像超分辨率重建在大尺度因子下存在训练不稳定、特征提取不足和重建结果纹理细节严重缺失的问题,提出一种拆分注意力网络的单图超分辨率重建方法。首先,以拆分注意力残差模块作为基本残差块构造生成器,提高生成器特征提取的能力。其次,在损失函数中引入鲁棒性更好的Charbonnier损失函数和Focal Frequency Loss损失函数代替均方差损失函数,同时加入正则化损失平滑训练结果,防止图像过于像素化。最后,在生成器和判别器中采用谱归一化处理,提高网络的稳定性。在4倍放大因子下,与其他方法在Set5、Set14、BSDS100、Urban100测试集上进行测试比较,本文方法的峰值信噪比比其他对比方法的平均值提升1.419 dB,结构相似性比其他对比方法的平均值提升0.051。实验数据和效果图表明,该方法主观上具有丰富的细节和更好的视觉效果,客观上具有较高的峰值信噪比值和结构相似度值。
基金supported by the National Natural Science Foundation of China(615730176140149961174162)
文摘Multiple complex networks, each with different properties and mutually fused, have the problems that the evolving process is time varying and non-equilibrium, network structures are layered and interlacing, and evolving characteristics are difficult to be measured. On that account, a dynamic evolving model of complex network with fusion nodes and overlap edges（CNFNOEs） is proposed. Firstly, we define some related concepts of CNFNOEs, and analyze the conversion process of fusion relationship and hierarchy relationship. According to the property difference of various nodes and edges, fusion nodes and overlap edges are subsequently split, and then the CNFNOEs is transformed to interlacing layered complex networks（ILCN）. Secondly,the node degree saturation and attraction factors are defined. On that basis, the evolution algorithm and the local world evolution model for ILCN are put forward. Moreover, four typical situations of nodes evolution are discussed, and the degree distribution law during evolution is analyzed by means of the mean field method.Numerical simulation results show that nodes unreached degree saturation follow the exponential distribution with an error of no more than 6%; nodes reached degree saturation follow the distribution of their connection capacities with an error of no more than 3%; network weaving coefficients have a positive correlation with the highest probability of new node and initial number of connected edges. The results have verified the feasibility and effectiveness of the model, which provides a new idea and method for exploring CNFNOE＇s evolving process and law. Also, the model has good application prospects in structure and dynamics research of transportation network, communication network, social contact network,etc.
文摘如何提取多尺度特征和建模远程通道间的语义依赖仍是表情识别网络面临的挑战。本文提出一种基于金字塔分割注意力的残差网络(Residual network based on pyramid split attention, PSA-ResNet)模型,该模型将ResNet50残差模块中的3×3卷积替换成金字塔分割注意力,以有效提取多尺度特征,增强跨通道语义信息的相关性。同时,为缩小同类表情之间的差异,扩大不同类表情之间的距离,在训练过程中引入了Softmax loss和Center loss联合损失函数优化模型参数。本文所提出的方法在Fer2013和CK+两个公开的数据集上进行仿真实验,分别取得了74.26%和98.35%的准确率,进一步证实了该方法相比前沿算法具有更好的表情识别效果。
