Imaging through fluctuating scattering media such as fog is of challenge since it seriously degrades the image quality.We investigate how the image quality of computational ghost imaging is reduced by fluctuating fog ...Imaging through fluctuating scattering media such as fog is of challenge since it seriously degrades the image quality.We investigate how the image quality of computational ghost imaging is reduced by fluctuating fog and how to obtain a high-quality defogging ghost image. We show theoretically and experimentally that the photon number fluctuations introduced by fluctuating fog is the reason for ghost image degradation. An algorithm is proposed to process the signals collected by the computational ghost imaging device to eliminate photon number fluctuations of different measurement events. Thus, a high-quality defogging ghost image is reconstructed even though fog is evenly distributed on the optical path. A nearly 100% defogging ghost image is obtained by further using a cycle generative adversarial network to process the reconstructed defogging image.展开更多
Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced...Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.展开更多
Generative adversarial networks(GANs)have shown impressive power in the field of machine learning.Traditional GANs have focused on unsupervised learning tasks.In recent years,conditional GANs that can generate data wi...Generative adversarial networks(GANs)have shown impressive power in the field of machine learning.Traditional GANs have focused on unsupervised learning tasks.In recent years,conditional GANs that can generate data with labels have been proposed in semi-supervised learning and have achieved better image quality than traditional GANs.Conditional GANs,however,generally only minimize the difference between marginal distributions of real and generated data,neglecting the difference with respect to each class of the data.To address this challenge,we propose the GAN with joint distribution moment matching(JDMM-GAN)for matching the joint distribution based on maximum mean discrepancy,which minimizes the differences of both the marginal and conditional distributions.The learning procedure is iteratively conducted by the stochastic gradient descent and back-propagation.We evaluate JDMM-GAN on several benchmark datasets,including MNIST,CIFAR-10 and the Extended Yale Face.Compared with the state-of-the-art GANs,JDMM-GAN generates more realistic images and achieves the best inception score for CIFAR-10 dataset.展开更多
基金supported by the Natural Science Foundation of Shandong Province, China (Grant No. ZR2022MF249)。
文摘Imaging through fluctuating scattering media such as fog is of challenge since it seriously degrades the image quality.We investigate how the image quality of computational ghost imaging is reduced by fluctuating fog and how to obtain a high-quality defogging ghost image. We show theoretically and experimentally that the photon number fluctuations introduced by fluctuating fog is the reason for ghost image degradation. An algorithm is proposed to process the signals collected by the computational ghost imaging device to eliminate photon number fluctuations of different measurement events. Thus, a high-quality defogging ghost image is reconstructed even though fog is evenly distributed on the optical path. A nearly 100% defogging ghost image is obtained by further using a cycle generative adversarial network to process the reconstructed defogging image.
基金supported by National Natural Science Foundation of China(Grant Nos.52279137,52009090).
文摘Estimation of construction parameters is crucial for optimizing tunnel construction schedule.Due to the influence of routine activities and occasional risk events,these parameters are usually correlated and imbalanced.To solve this issue,an improved bidirectional generative adversarial network(BiGAN)model with a joint discriminator structure and zero-centered gradient penalty(0-GP)is proposed.In this model,in order to improve the capability of original BiGAN in learning imbalanced parameters,the joint discriminator separately discriminates the routine activities and risk event durations to balance their influence weights.Then,the self-attention mechanism is embedded so that the discriminator can pay more attention to the imbalanced parameters.Finally,the 0-GP is adapted for the loss of the discrimi-nator to improve its convergence and stability.A case study of a tunnel in China shows that the improved BiGAN can obtain parameter estimates consistent with the classical Gauss mixture model,without the need of tedious and complex correlation analysis.The proposed joint discriminator can increase the ability of BiGAN in estimating imbalanced construction parameters,and the 0-GP can ensure the stability and convergence of the model.
基金This work is supported by the National Natural Science Foundation of China(Nos.11771276,11471208,61731009)the Foundation of Science and Technology Commission of Shanghai Municipality(No.14DZ2260800).
文摘Generative adversarial networks(GANs)have shown impressive power in the field of machine learning.Traditional GANs have focused on unsupervised learning tasks.In recent years,conditional GANs that can generate data with labels have been proposed in semi-supervised learning and have achieved better image quality than traditional GANs.Conditional GANs,however,generally only minimize the difference between marginal distributions of real and generated data,neglecting the difference with respect to each class of the data.To address this challenge,we propose the GAN with joint distribution moment matching(JDMM-GAN)for matching the joint distribution based on maximum mean discrepancy,which minimizes the differences of both the marginal and conditional distributions.The learning procedure is iteratively conducted by the stochastic gradient descent and back-propagation.We evaluate JDMM-GAN on several benchmark datasets,including MNIST,CIFAR-10 and the Extended Yale Face.Compared with the state-of-the-art GANs,JDMM-GAN generates more realistic images and achieves the best inception score for CIFAR-10 dataset.
