Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as con...Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as convergence difficulty,model collapse,etc.In this work,an end-to-end speech enhancement model based on Wasserstein Generative Adversarial Networks is proposed,and some improvements have been made in order to get faster convergence speed and better generated speech quality.Specifically,in the generator coding part,each convolution layer adopts different convolution kernel sizes to conduct convolution operations for obtaining speech coding information from multiple scales;a gated linear unit is introduced to alleviate the vanishing gradient problem with the increase of network depth;the gradient penalty of the discriminator is replaced with spectral normalization to accelerate the convergence rate of themodel;a hybrid penalty termcomposed of L1 regularization and a scale-invariant signal-to-distortion ratio is introduced into the loss function of the generator to improve the quality of generated speech.The experimental results on both TIMIT corpus and Tibetan corpus show that the proposed model improves the speech quality significantly and accelerates the convergence speed of the model.展开更多
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea...In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.展开更多
The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image...The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.展开更多
This research addresses the critical challenge of enhancing satellite images captured under low-light conditions,which suffer from severely degraded quality,including a lack of detail,poor contrast,and low usability.O...This research addresses the critical challenge of enhancing satellite images captured under low-light conditions,which suffer from severely degraded quality,including a lack of detail,poor contrast,and low usability.Overcoming this limitation is essential for maximizing the value of satellite imagery in downstream computer vision tasks(e.g.,spacecraft on-orbit connection,spacecraft surface repair,space debris capture)that rely on clear visual information.Our key novelty lies in an unsupervised generative adversarial network featuring two main contributions:(1)an improved U-Net(IU-Net)generator with multi-scale feature fusion in the contracting path for richer semantic feature extraction,and(2)a Global Illumination Attention Module(GIA)at the end of the contracting path to couple local and global information,significantly improving detail recovery and illumination adjustment.The proposed algorithm operates in an unsupervised manner.It is trained and evaluated on our self-constructed,unpaired Spacecraft Dataset for Detection,Enforcement,and Parts Recognition(SDDEP),designed specifically for low-light enhancement tasks.Extensive experiments demonstrate that our method outperforms the baseline EnlightenGAN,achieving improvements of 2.7%in structural similarity(SSIM),4.7%in peak signal-to-noise ratio(PSNR),6.3%in learning perceptual image patch similarity(LPIPS),and 53.2%in DeltaE 2000.Qualitatively,the enhanced images exhibit higher overall and local brightness,improved contrast,and more natural visual effects.展开更多
Purpose-Clothing patterns play a dominant role in costume design and have become an important link in the perception of costume art.Conventional clothing patterns design relies on experienced designers.Although the qu...Purpose-Clothing patterns play a dominant role in costume design and have become an important link in the perception of costume art.Conventional clothing patterns design relies on experienced designers.Although the quality of clothing patterns is very high on conventional design,the input time and output amount ratio is relative low for conventional design.In order to break through the bottleneck of conventional clothing patterns design,this paper proposes a novel way based on generative adversarial network(GAN)model for automatic clothing patterns generation,which not only reduces the dependence of experienced designer,but also improve the input-output ratio.Design/methodology/approach-In view of the fact that clothing patterns have high requirements for global artistic perception and local texture details,this paper improves the conventional GAN model from two aspects:a multi-scales discriminators strategy is introduced to deal with the local texture details;and the selfattention mechanism is introduced to improve the global artistic perception.Therefore,the improved GAN called multi-scales self-attention improved generative adversarial network(MS-SA-GAN)model,which is used for high resolution clothing patterns generation.Findings-To verify the feasibility and effectiveness of the proposed MS-SA-GAN model,a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures,and a comparative experiment is conducted on our designed clothing patterns dataset.In experiments,we have adjusted different parameters of the proposed MS-SA-GAN model,and compared the global artistic perception and local texture details of the generated clothing patterns.Originality/value-Experimental results have shown that the clothing patterns generated by the proposed MS-SA-GANmodel are superior to the conventional algorithms in some local texture detail indexes.In addition,a group of clothing design professionals is invited to evaluate the global artistic perception through a valencearousal scale.The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.展开更多
Deep neural networks are commonly used in computer vision tasks,but they are vulnerable to adversarial samples,resulting in poor recognition accuracy.Although traditional algorithms that craft adversarial samples have...Deep neural networks are commonly used in computer vision tasks,but they are vulnerable to adversarial samples,resulting in poor recognition accuracy.Although traditional algorithms that craft adversarial samples have been effective in attacking classification models,the attacking performance degrades when facing object detection models with more complex structures.To address this issue better,in this paper we first analyze the mechanism of multi-scale feature extraction of object detection models,and then by constructing the object feature-wise attention module and the perturbation extraction module,a novel adversarial sample generation algorithm for attacking detection models is proposed.Specifically,in the first module,based on the multi-scale feature map,we reduce the range of perturbation and improve the stealthiness of adversarial samples by computing the noise distribution in the object region.Then in the second module,we feed the noise distribution into the generative adversarial networks to generate adversarial perturbation with strong attack transferability.By doing so,the proposed approach possesses the ability to better confuse the judgment of detection models.Experiments carried out on the DroneVehicle dataset show that our method is computationally efficient and works well in attacking detection models measured by qualitative analysis and quantitative analysis.展开更多
基金supported by the National Science Foundation under Grant No.62066039.
文摘Recently,speech enhancement methods based on Generative Adversarial Networks have achieved good performance in time-domain noisy signals.However,the training of Generative Adversarial Networks has such problems as convergence difficulty,model collapse,etc.In this work,an end-to-end speech enhancement model based on Wasserstein Generative Adversarial Networks is proposed,and some improvements have been made in order to get faster convergence speed and better generated speech quality.Specifically,in the generator coding part,each convolution layer adopts different convolution kernel sizes to conduct convolution operations for obtaining speech coding information from multiple scales;a gated linear unit is introduced to alleviate the vanishing gradient problem with the increase of network depth;the gradient penalty of the discriminator is replaced with spectral normalization to accelerate the convergence rate of themodel;a hybrid penalty termcomposed of L1 regularization and a scale-invariant signal-to-distortion ratio is introduced into the loss function of the generator to improve the quality of generated speech.The experimental results on both TIMIT corpus and Tibetan corpus show that the proposed model improves the speech quality significantly and accelerates the convergence speed of the model.
文摘In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
文摘The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.
基金supported by Anhui Province University Key Science and Technology Project(2024AH053415)Anhui Province University Major Science and Technology Project(2024AH040229).
文摘This research addresses the critical challenge of enhancing satellite images captured under low-light conditions,which suffer from severely degraded quality,including a lack of detail,poor contrast,and low usability.Overcoming this limitation is essential for maximizing the value of satellite imagery in downstream computer vision tasks(e.g.,spacecraft on-orbit connection,spacecraft surface repair,space debris capture)that rely on clear visual information.Our key novelty lies in an unsupervised generative adversarial network featuring two main contributions:(1)an improved U-Net(IU-Net)generator with multi-scale feature fusion in the contracting path for richer semantic feature extraction,and(2)a Global Illumination Attention Module(GIA)at the end of the contracting path to couple local and global information,significantly improving detail recovery and illumination adjustment.The proposed algorithm operates in an unsupervised manner.It is trained and evaluated on our self-constructed,unpaired Spacecraft Dataset for Detection,Enforcement,and Parts Recognition(SDDEP),designed specifically for low-light enhancement tasks.Extensive experiments demonstrate that our method outperforms the baseline EnlightenGAN,achieving improvements of 2.7%in structural similarity(SSIM),4.7%in peak signal-to-noise ratio(PSNR),6.3%in learning perceptual image patch similarity(LPIPS),and 53.2%in DeltaE 2000.Qualitatively,the enhanced images exhibit higher overall and local brightness,improved contrast,and more natural visual effects.
基金This paper is supported by university fund project of Hubei Institute of Fine Arts,named“The construction of blended teaching mode based on flipped classroom-Taking the Course of“Fashion Painting Illustration”as an Example.”(No.202028)。
文摘Purpose-Clothing patterns play a dominant role in costume design and have become an important link in the perception of costume art.Conventional clothing patterns design relies on experienced designers.Although the quality of clothing patterns is very high on conventional design,the input time and output amount ratio is relative low for conventional design.In order to break through the bottleneck of conventional clothing patterns design,this paper proposes a novel way based on generative adversarial network(GAN)model for automatic clothing patterns generation,which not only reduces the dependence of experienced designer,but also improve the input-output ratio.Design/methodology/approach-In view of the fact that clothing patterns have high requirements for global artistic perception and local texture details,this paper improves the conventional GAN model from two aspects:a multi-scales discriminators strategy is introduced to deal with the local texture details;and the selfattention mechanism is introduced to improve the global artistic perception.Therefore,the improved GAN called multi-scales self-attention improved generative adversarial network(MS-SA-GAN)model,which is used for high resolution clothing patterns generation.Findings-To verify the feasibility and effectiveness of the proposed MS-SA-GAN model,a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures,and a comparative experiment is conducted on our designed clothing patterns dataset.In experiments,we have adjusted different parameters of the proposed MS-SA-GAN model,and compared the global artistic perception and local texture details of the generated clothing patterns.Originality/value-Experimental results have shown that the clothing patterns generated by the proposed MS-SA-GANmodel are superior to the conventional algorithms in some local texture detail indexes.In addition,a group of clothing design professionals is invited to evaluate the global artistic perception through a valencearousal scale.The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.
基金supported in part by the Natural Science Foundation of the Anhui Higher Education Institutions of China(Nos.2023AH040149 and 2022AH050310)the Anhui Provincial Natural Science Foundation(No.2208085MF168)+1 种基金the Science and Technology Innovation Program of Maanshan,China(No.2021a120009)the National Natural Science Foundation of China(Nos.52205548,62206006,and 62306007).
文摘Deep neural networks are commonly used in computer vision tasks,but they are vulnerable to adversarial samples,resulting in poor recognition accuracy.Although traditional algorithms that craft adversarial samples have been effective in attacking classification models,the attacking performance degrades when facing object detection models with more complex structures.To address this issue better,in this paper we first analyze the mechanism of multi-scale feature extraction of object detection models,and then by constructing the object feature-wise attention module and the perturbation extraction module,a novel adversarial sample generation algorithm for attacking detection models is proposed.Specifically,in the first module,based on the multi-scale feature map,we reduce the range of perturbation and improve the stealthiness of adversarial samples by computing the noise distribution in the object region.Then in the second module,we feed the noise distribution into the generative adversarial networks to generate adversarial perturbation with strong attack transferability.By doing so,the proposed approach possesses the ability to better confuse the judgment of detection models.Experiments carried out on the DroneVehicle dataset show that our method is computationally efficient and works well in attacking detection models measured by qualitative analysis and quantitative analysis.
