As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capaci...As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capacity.However,existing VQ-VAEs often perform quantization in the spatial domain,ignoring global structural information and potentially suffering from codebook collapse and information coupling issues.This paper proposes a frequency quantized variational autoencoder(FQ-VAE)to address these issues.The proposed method transforms image features into linear combinations in the frequency domain using a 2D fast Fourier transform(2D-FFT)and performs adaptive quantization on these frequency components to preserve image’s global relationships.The codebook is dynamically optimized to avoid collapse and information coupling issue by considering the usage frequency and dependency of code vectors.Furthermore,we introduce a post-processing module based on graph convolutional networks to further improve reconstruction quality.Experimental results on four public datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of Structural Similarity Index(SSIM),Learned Perceptual Image Patch Similarity(LPIPS),and Reconstruction Fréchet Inception Distance(rFID).In the experiments on the CIFAR-10 dataset,compared to the baselinemethod VQ-VAE,the proposedmethod improves the abovemetrics by 4.9%,36.4%,and 52.8%,respectively.展开更多
We put forward a multicore parallel plan for 2D-FFT and implement it on TMS320C6678 DSP after we research thecharacteristics of different multicore DSP programming models and two-dimension FFT （2D-FFT）. We bring the...We put forward a multicore parallel plan for 2D-FFT and implement it on TMS320C6678 DSP after we research thecharacteristics of different multicore DSP programming models and two-dimension FFT （2D-FFT）. We bring the parallelcomputing capability of multicore DSP into full play and improve working efficiency of 2D-FFT. It has hugely referential valuein implementing image processing arithmetic based on 2D-FFT.展开更多
针对通信感知一体化(Integrated Sensing and Communication,ISAC)系统中基于正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)不同星座概率调制的目标距离、速度与角度估计面临的时延-多普勒耦合及波形适配性不明确等问...针对通信感知一体化(Integrated Sensing and Communication,ISAC)系统中基于正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)不同星座概率调制的目标距离、速度与角度估计面临的时延-多普勒耦合及波形适配性不明确等问题,文中提出了一种融合二维快速傅里叶变换(2D-FFT)与多重信号分类(Multiple Signal Classification,MUSIC)算法的联合参数估计算法。首先,设计了基于2D-FFT的距离与速度估计算法,通过频域-时域联合变换解耦时延-多普勒耦合项,实现多目标场景下的参数分离;其次,利用MUSIC算法对ISAC信号进行处理,基于子空间正交性提升到达角(Angle of Arrival,AoA)估计精度;最后,通过仿真对比了通信最优的复高斯分布与感知最优的QPSK两种星座分布下的性能。结果表明,所提算法可有效实现目标参数的高精度估计,且在相同信噪比下QPSK星座的估计精度优于复高斯分布。本文研究为OFDM-based ISAC系统的参数估计算法设计与波形选择提供了理论依据与仿真支撑。展开更多
基金supported by the Interdisciplinary project of Dalian University DLUXK-2023-ZD-001.
文摘As a form of discrete representation learning,Vector Quantized Variational Autoencoders(VQ-VAE)have increasingly been applied to generative and multimodal tasks due to their ease of embedding and representative capacity.However,existing VQ-VAEs often perform quantization in the spatial domain,ignoring global structural information and potentially suffering from codebook collapse and information coupling issues.This paper proposes a frequency quantized variational autoencoder(FQ-VAE)to address these issues.The proposed method transforms image features into linear combinations in the frequency domain using a 2D fast Fourier transform(2D-FFT)and performs adaptive quantization on these frequency components to preserve image’s global relationships.The codebook is dynamically optimized to avoid collapse and information coupling issue by considering the usage frequency and dependency of code vectors.Furthermore,we introduce a post-processing module based on graph convolutional networks to further improve reconstruction quality.Experimental results on four public datasets demonstrate that the proposed method outperforms state-of-the-art approaches in terms of Structural Similarity Index(SSIM),Learned Perceptual Image Patch Similarity(LPIPS),and Reconstruction Fréchet Inception Distance(rFID).In the experiments on the CIFAR-10 dataset,compared to the baselinemethod VQ-VAE,the proposedmethod improves the abovemetrics by 4.9%,36.4%,and 52.8%,respectively.
文摘We put forward a multicore parallel plan for 2D-FFT and implement it on TMS320C6678 DSP after we research thecharacteristics of different multicore DSP programming models and two-dimension FFT （2D-FFT）. We bring the parallelcomputing capability of multicore DSP into full play and improve working efficiency of 2D-FFT. It has hugely referential valuein implementing image processing arithmetic based on 2D-FFT.
文摘针对通信感知一体化(Integrated Sensing and Communication,ISAC)系统中基于正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)不同星座概率调制的目标距离、速度与角度估计面临的时延-多普勒耦合及波形适配性不明确等问题,文中提出了一种融合二维快速傅里叶变换(2D-FFT)与多重信号分类(Multiple Signal Classification,MUSIC)算法的联合参数估计算法。首先,设计了基于2D-FFT的距离与速度估计算法,通过频域-时域联合变换解耦时延-多普勒耦合项,实现多目标场景下的参数分离;其次,利用MUSIC算法对ISAC信号进行处理,基于子空间正交性提升到达角(Angle of Arrival,AoA)估计精度;最后,通过仿真对比了通信最优的复高斯分布与感知最优的QPSK两种星座分布下的性能。结果表明,所提算法可有效实现目标参数的高精度估计,且在相同信噪比下QPSK星座的估计精度优于复高斯分布。本文研究为OFDM-based ISAC系统的参数估计算法设计与波形选择提供了理论依据与仿真支撑。
