This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution ...This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution of a class of data is close to a low-dimensional manifold.GANs mainly accomplish two tasks:manifold learning and probability distribution transformation.The latter can be carried out using the classical OT method.From the OT perspective,the generator computes the OT map,while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution;both can be reduced to a convex geometric optimization process.Furthermore,OT theory discovers the intrinsic collaborative-instead of competitive-relation between the generator and the discriminator,and the fundamental reason for mode collapse.We also propose a novel generative model,which uses an autoencoder(AE)for manifold learning and OT map for probability distribution transformation.This AE–OT model improves the theoretical rigor and transparency,as well as the computational stability and efficiency;in particular,it eliminates the mode collapse.The experimental results validate our hypothesis,and demonstrate the advantages of our proposed model.展开更多
Medical image generation has recently garnered significant interest among researchers.However,the primary generative models,such as Generative Adversarial Networks(GANs),often encounter challenges during training,incl...Medical image generation has recently garnered significant interest among researchers.However,the primary generative models,such as Generative Adversarial Networks(GANs),often encounter challenges during training,including mode collapse.To address these issues,we proposed the AECOT-GAN model(Autoencoder-based Conditional Optimal Transport Generative Adversarial Network)for the generation of medical images belonging to specific categories.The training process of our model comprises three fundamental components.The training process of our model encompasses three fundamental components.First,we employ an autoencoder model to obtain a low-dimensional manifold representation of real images.Second,we apply extended semi-discrete optimal transport to map Gaussian noise distribution to the latent space distribution and obtain corresponding labels effectively.This procedure leads to the generation of new latent codes with known labels.Finally,we integrate a GAN to train the decoder further to generate medical images.To evaluate the performance of the AE-COT-GAN model,we conducted experiments on two medical image datasets,namely DermaMNIST and BloodMNIST.The model’s performance was compared with state-of-the-art generative models.Results show that the AE-COT-GAN model had excellent performance in generating medical images.Moreover,it effectively addressed the common issues associated with traditional GANs.展开更多
In this paper,we apply the material point method(MPM),also known as a meshfree method,to examine the crush behaviour of thin tubular columns.Unlike the finite element method,randomly-distributed-weak-particle triggers...In this paper,we apply the material point method(MPM),also known as a meshfree method,to examine the crush behaviour of thin tubular columns.Unlike the finite element method,randomly-distributed-weak-particle triggers were used to account for the deformation behaviour of collapse modes.Both symmetric and asymmetric modes of deformation and their associated mean collapse loads are determined for an elasto-plastic constitutive law describing the tubular columns.Attention was devoted to the accuracy and the convergence of the MPM simulation,which is determined by the number of the particles and the size of the background cells used in our explicit solver.Furthermore,a novel contact approach was adopted to establish the crush behaviour of the tubular columns.Two aspects of the work were accordingly examined,including three different crush velocities(5,10 and 15 m/s) and varied geometrical features of the tube(t/d and l/d) based on the deformation history.The results of our model,which were compared with existing analytical predictions and experimental findings,identify the critical geometric features of the tubular columns that would dictate the deformation mode as being either progressive collapse or following Euler's buckling mode.展开更多
近年来,虽然基于生成对抗网络(generative adversarial networks,GAN)的文本生成图像问题取得了很大的突破,它可以根据文本的语义信息生成相应的图像,但是生成的图像结果通常缺乏具体的纹理细节,并且经常出现模式崩塌、缺乏多样性等问...近年来,虽然基于生成对抗网络(generative adversarial networks,GAN)的文本生成图像问题取得了很大的突破,它可以根据文本的语义信息生成相应的图像,但是生成的图像结果通常缺乏具体的纹理细节,并且经常出现模式崩塌、缺乏多样性等问题。针对以上问题,提出一种针对生成对抗网络的行列式点过程(determinant point process for generative adversarial networks,GAN-DPP)方法来提高模型生成样本的质量,并使用StackGAN++、ControlGAN两种基线模型对GAN-DPP进行实现。在训练过程中,该方法使用行列式点过程核矩阵对真实数据和合成数据的多样性进行建模,并通过引入无监督惩罚损失来鼓励生成器生成与真实数据相似的多样性数据,从而提高生成样本的清晰度及多样性,减轻模型崩塌等问题,并且无需增加额外的训练过程。在CUB和Oxford-102数据集上,通过Inception Score、Fréchet Inception Distance分数、Human Rank这3种指标的定量评估,证明了GAN-DPP对生成图像多样性与质量提升的有效性。同时通过定性的可视化比较,证明使用GAN-DPP的模型生成的图像纹理细节更加丰富,多样性显著提高。展开更多
基金the National Natural Science Foundation of China(61936002,61772105,61432003,61720106005,and 61772379)US National Science Foundation(NSF)CMMI-1762287 collaborative research“computational framework for designing conformal stretchable electronics,Ford URP topology optimization of cellular mesostructures’nonlinear behaviors for crash safety,”NSF DMS-1737812 collaborative research“ATD:theory and algorithms for discrete curvatures on network data from human mobility and monitoring.”。
文摘This work introduces an optimal transportation(OT)view of generative adversarial networks(GANs).Natural datasets have intrinsic patterns,which can be summarized as the manifold distribution principle:the distribution of a class of data is close to a low-dimensional manifold.GANs mainly accomplish two tasks:manifold learning and probability distribution transformation.The latter can be carried out using the classical OT method.From the OT perspective,the generator computes the OT map,while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution;both can be reduced to a convex geometric optimization process.Furthermore,OT theory discovers the intrinsic collaborative-instead of competitive-relation between the generator and the discriminator,and the fundamental reason for mode collapse.We also propose a novel generative model,which uses an autoencoder(AE)for manifold learning and OT map for probability distribution transformation.This AE–OT model improves the theoretical rigor and transparency,as well as the computational stability and efficiency;in particular,it eliminates the mode collapse.The experimental results validate our hypothesis,and demonstrate the advantages of our proposed model.
基金the National Key R&D Program of China under Grant No.2022ZD0117000the National Institutes of Health,United States under award number 3R01LM012434-05S1 and 1R21EB029733-01A1the National Science Foundation,United States under Grant No.FAIN-2115095 and Grant No.CMMI-1762287.
文摘Medical image generation has recently garnered significant interest among researchers.However,the primary generative models,such as Generative Adversarial Networks(GANs),often encounter challenges during training,including mode collapse.To address these issues,we proposed the AECOT-GAN model(Autoencoder-based Conditional Optimal Transport Generative Adversarial Network)for the generation of medical images belonging to specific categories.The training process of our model comprises three fundamental components.The training process of our model encompasses three fundamental components.First,we employ an autoencoder model to obtain a low-dimensional manifold representation of real images.Second,we apply extended semi-discrete optimal transport to map Gaussian noise distribution to the latent space distribution and obtain corresponding labels effectively.This procedure leads to the generation of new latent codes with known labels.Finally,we integrate a GAN to train the decoder further to generate medical images.To evaluate the performance of the AE-COT-GAN model,we conducted experiments on two medical image datasets,namely DermaMNIST and BloodMNIST.The model’s performance was compared with state-of-the-art generative models.Results show that the AE-COT-GAN model had excellent performance in generating medical images.Moreover,it effectively addressed the common issues associated with traditional GANs.
基金supported by the National Basic Research Program of China (Grant No. 2010CB832701)Natural Sciences and Engineering Research Council of Canada (NSERC)
文摘In this paper,we apply the material point method(MPM),also known as a meshfree method,to examine the crush behaviour of thin tubular columns.Unlike the finite element method,randomly-distributed-weak-particle triggers were used to account for the deformation behaviour of collapse modes.Both symmetric and asymmetric modes of deformation and their associated mean collapse loads are determined for an elasto-plastic constitutive law describing the tubular columns.Attention was devoted to the accuracy and the convergence of the MPM simulation,which is determined by the number of the particles and the size of the background cells used in our explicit solver.Furthermore,a novel contact approach was adopted to establish the crush behaviour of the tubular columns.Two aspects of the work were accordingly examined,including three different crush velocities(5,10 and 15 m/s) and varied geometrical features of the tube(t/d and l/d) based on the deformation history.The results of our model,which were compared with existing analytical predictions and experimental findings,identify the critical geometric features of the tubular columns that would dictate the deformation mode as being either progressive collapse or following Euler's buckling mode.
文摘近年来,虽然基于生成对抗网络(generative adversarial networks,GAN)的文本生成图像问题取得了很大的突破,它可以根据文本的语义信息生成相应的图像,但是生成的图像结果通常缺乏具体的纹理细节,并且经常出现模式崩塌、缺乏多样性等问题。针对以上问题,提出一种针对生成对抗网络的行列式点过程(determinant point process for generative adversarial networks,GAN-DPP)方法来提高模型生成样本的质量,并使用StackGAN++、ControlGAN两种基线模型对GAN-DPP进行实现。在训练过程中,该方法使用行列式点过程核矩阵对真实数据和合成数据的多样性进行建模,并通过引入无监督惩罚损失来鼓励生成器生成与真实数据相似的多样性数据,从而提高生成样本的清晰度及多样性,减轻模型崩塌等问题,并且无需增加额外的训练过程。在CUB和Oxford-102数据集上,通过Inception Score、Fréchet Inception Distance分数、Human Rank这3种指标的定量评估,证明了GAN-DPP对生成图像多样性与质量提升的有效性。同时通过定性的可视化比较,证明使用GAN-DPP的模型生成的图像纹理细节更加丰富,多样性显著提高。
