Mechanically cleaved two-dimensional materials are random in size and thickness.Recognizing atomically thin flakes by human experts is inefficient and unsuitable for scalable production.Deep learning algorithms have b...Mechanically cleaved two-dimensional materials are random in size and thickness.Recognizing atomically thin flakes by human experts is inefficient and unsuitable for scalable production.Deep learning algorithms have been adopted as an alternative,nevertheless a major challenge is a lack of sufficient actual training images.Here we report the generation of synthetic two-dimensional materials images using StyleGAN3 to complement the dataset.DeepLabv3Plus network is trained with the synthetic images which reduces overfitting and improves recognition accuracy to over 90%.A semi-supervisory technique for labeling images is introduced to reduce manual efforts.The sharper edges recognized by this method facilitate material stacking with precise edge alignment,which benefits exploring novel properties of layered-material devices that crucially depend on the interlayer twist-angle.This feasible and efficient method allows for the rapid and high-quality manufacturing of atomically thin materials and devices.展开更多
Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative ad...Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative adversarial network.This model includes two modules,generator and adversary.Generator is mainly used to generate images embedded with watermark,and decode the image damaged by noise to obtain the watermark.Adversary is used to discriminate whether the image is embedded with watermark and damage the image by noise.Based on the model Hidden(hiding data with deep networks),we add a high-pass filter in front of the discriminator,making the watermark tend to be embedded in the mid-frequency region of the image.Since the human visual system pays more attention to the central area of the image,we give a higher weight to the image center region,and a lower weight to the edge region when calculating the loss between cover and embedded image.The watermarked image obtained by this scheme has a better visual performance.Experimental results show that the proposed architecture is more robust against noise interference compared with the state-of-art schemes.展开更多
Ground military target recognition plays a crucial role in unmanned equipment and grasping the battlefield dynamics for military applications, but is disturbed by low-resolution and noisyrepresentation. In this paper,...Ground military target recognition plays a crucial role in unmanned equipment and grasping the battlefield dynamics for military applications, but is disturbed by low-resolution and noisyrepresentation. In this paper, a recognition method, involving a novel visual attention mechanismbased Gabor region proposal sub-network(Gabor RPN) and improved refinement generative adversarial sub-network(GAN), is proposed. Novel central-peripheral rivalry 3D color Gabor filters are proposed to simulate retinal structures and taken as feature extraction convolutional kernels in low-level layer to improve the recognition accuracy and framework training efficiency in Gabor RPN. Improved refinement GAN is used to solve the problem of blurry target classification, involving a generator to directly generate large high-resolution images from small blurry ones and a discriminator to distinguish not only real images vs. fake images but also the class of targets. A special recognition dataset for ground military target, named Ground Military Target Dataset(GMTD), is constructed. Experiments performed on the GMTD dataset effectively demonstrate that our method can achieve better energy-saving and recognition results when low-resolution and noisy-representation targets are involved, thus ensuring this algorithm a good engineering application prospect.展开更多
Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss...Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.展开更多
In this paper,we propose a hybrid model aiming to map the input noise vector to the label of the generated image by the generative adversarial network(GAN).This model mainly consists of a pre-trained deep convolution ...In this paper,we propose a hybrid model aiming to map the input noise vector to the label of the generated image by the generative adversarial network(GAN).This model mainly consists of a pre-trained deep convolution generative adversarial network(DCGAN)and a classifier.By using the model,we visualize the distribution of two-dimensional input noise,leading to a specific type of the generated image after each training epoch of GAN.The visualization reveals the distribution feature of the input noise vector and the performance of the generator.With this feature,we try to build a guided generator(GG)with the ability to produce a fake image we need.Two methods are proposed to build GG.One is the most significant noise(MSN)method,and the other utilizes labeled noise.The MSN method can generate images precisely but with less variations.In contrast,the labeled noise method has more variations but is slightly less stable.Finally,we propose a criterion to measure the performance of the generator,which can be used as a loss function to effectively train the network.展开更多
Spectrum prediction is one of the new techniques in cognitive radio that predicts changes in the spectrum state and plays a crucial role in improving spectrum sensing performance.Prediction models previously trained i...Spectrum prediction is one of the new techniques in cognitive radio that predicts changes in the spectrum state and plays a crucial role in improving spectrum sensing performance.Prediction models previously trained in the source band tend to perform poorly in the new target band because of changes in the channel.In addition,cognitive radio devices require dynamic spectrum access,which means that the time to retrain the model in the new band is minimal.To increase the amount of data in the target band,we use the GAN to convert the data of source band into target band.First,we analyze the data differences between bands and calculate FID scores to identify the available bands with the slightest difference from the target predicted band.The original GAN structure is unsuitable for converting spectrum data,and we propose the spectrum data conversion GAN(SDC-GAN).The generator module consists of a convolutional network and an LSTM module that can integrate multiple features of the data and can convert data from the source band to the target band.Finally,we use the generated target band data to train the prediction model.The experimental results validate the effectiveness of the proposed algorithm.展开更多
Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant chal...Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant challenge.With the availability of open data and software,coupled with automated simulations,deep learning has become an integral component of battery health prognostics.We offer a comprehensive overview of potential deep learning techniques specifically designed for modeling and forecasting the dynamics of multiphysics and multiscale battery systems.Following this,we provide a concise summary of publicly available lithium-ion battery test and cycle datasets.By providing illustrative examples,we emphasize the efficacy of five techniques capable of enhancing deep learning for accurate battery state prediction and health-focused management.Each of these techniques offers unique benefits.(1)Transformer models address challenges using self-attention mechanisms and positional encoding methods.(2) Transfer learning improves learning tasks within a target domain by leveraging knowledge from a source domain.(3) Physics-informed learning uses prior knowledge to enhance learning algorithms.(4)Generative adversarial networks(GANs) earn praise for their ability to generate diverse and high-quality outputs,exhibiting outstanding performance with complex datasets.(5) Deep reinforcement learning enables an agent to make optimal decisions through continuous interactions with its environment,thus maximizing cumulative rewards.In this Review,we highlight examples that employ these techniques for battery health prognostics,summarizing both their challenges and opportunities.These methodologies offer promising prospects for researchers and industry professionals,enabling the creation of specialized network architectures that autonomously extract features,especially for long-range spatial-temporal connections across extended timescales.The outcomes could include improved accuracy,faster training,and enhanced generalization.展开更多
The automatic stealth task of military time-sensitive targets plays a crucial role in maintaining national military security and mastering battlefield dynamics in military applications.We propose a novel Military Time...The automatic stealth task of military time-sensitive targets plays a crucial role in maintaining national military security and mastering battlefield dynamics in military applications.We propose a novel Military Time-sensitive Targets Stealth Network via Real-time Mask Generation(MTTSNet).According to our knowledge,this is the first technology to automatically remove military targets in real-time from videos.The critical steps of MTTSNet are as follows:First,we designed a real-time mask generation network based on the encoder-decoder framework,combined with the domain expansion structure,to effectively extract mask images.Specifically,the ASPP structure in the encoder could achieve advanced semantic feature fusion.The decoder stacked high-dimensional information with low-dimensional information to obtain an effective mask layer.Subsequently,the domain expansion module guided the adaptive expansion of mask images.Second,a context adversarial generation network based on gated convolution was constructed to achieve background restoration of mask positions in the original image.In addition,our method worked in an end-to-end manner.A particular semantic segmentation dataset for military time-sensitive targets has been constructed,called the Military Time-sensitive Target Masking Dataset(MTMD).The MTMD dataset experiment successfully demonstrated that this method could create a mask that completely occludes the target and that the target could be hidden in real time using this mask.We demonstrated the concealment performance of our proposed method by comparing it to a number of well-known and highly optimized baselines.展开更多
基金Project supported by the National Key Research and Development Program of China(Grant No.2022YFB2803900)the National Natural Science Foundation of China(Grant Nos.61974075 and 61704121)+2 种基金the Natural Science Foundation of Tianjin Municipality(Grant Nos.22JCZDJC00460 and 19JCQNJC00700)Tianjin Municipal Education Commission(Grant No.2019KJ028)Fundamental Research Funds for the Central Universities(Grant No.22JCZDJC00460).
文摘Mechanically cleaved two-dimensional materials are random in size and thickness.Recognizing atomically thin flakes by human experts is inefficient and unsuitable for scalable production.Deep learning algorithms have been adopted as an alternative,nevertheless a major challenge is a lack of sufficient actual training images.Here we report the generation of synthetic two-dimensional materials images using StyleGAN3 to complement the dataset.DeepLabv3Plus network is trained with the synthetic images which reduces overfitting and improves recognition accuracy to over 90%.A semi-supervisory technique for labeling images is introduced to reduce manual efforts.The sharper edges recognized by this method facilitate material stacking with precise edge alignment,which benefits exploring novel properties of layered-material devices that crucially depend on the interlayer twist-angle.This feasible and efficient method allows for the rapid and high-quality manufacturing of atomically thin materials and devices.
基金supported by the National Natural Science Foundation of China under Grants 62072295,61525203,U1636206,U1936214Natural Science Foundation of Shanghai under Grant 19ZR1419000。
文摘Digital watermark embeds information bits into digital cover such as images and videos to prove the creator’s ownership of his work.In this paper,we propose a robust image watermark algorithm based on a generative adversarial network.This model includes two modules,generator and adversary.Generator is mainly used to generate images embedded with watermark,and decode the image damaged by noise to obtain the watermark.Adversary is used to discriminate whether the image is embedded with watermark and damage the image by noise.Based on the model Hidden(hiding data with deep networks),we add a high-pass filter in front of the discriminator,making the watermark tend to be embedded in the mid-frequency region of the image.Since the human visual system pays more attention to the central area of the image,we give a higher weight to the image center region,and a lower weight to the edge region when calculating the loss between cover and embedded image.The watermarked image obtained by this scheme has a better visual performance.Experimental results show that the proposed architecture is more robust against noise interference compared with the state-of-art schemes.
基金the National Key Research and Development Program of China(No.2016YFC0802904)National Natural Science Foundation of China(No.61671470)Natural Science Foundation of Jiangsu Province(BK20161470).
文摘Ground military target recognition plays a crucial role in unmanned equipment and grasping the battlefield dynamics for military applications, but is disturbed by low-resolution and noisyrepresentation. In this paper, a recognition method, involving a novel visual attention mechanismbased Gabor region proposal sub-network(Gabor RPN) and improved refinement generative adversarial sub-network(GAN), is proposed. Novel central-peripheral rivalry 3D color Gabor filters are proposed to simulate retinal structures and taken as feature extraction convolutional kernels in low-level layer to improve the recognition accuracy and framework training efficiency in Gabor RPN. Improved refinement GAN is used to solve the problem of blurry target classification, involving a generator to directly generate large high-resolution images from small blurry ones and a discriminator to distinguish not only real images vs. fake images but also the class of targets. A special recognition dataset for ground military target, named Ground Military Target Dataset(GMTD), is constructed. Experiments performed on the GMTD dataset effectively demonstrate that our method can achieve better energy-saving and recognition results when low-resolution and noisy-representation targets are involved, thus ensuring this algorithm a good engineering application prospect.
文摘Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.
基金supported by Shenzhen Science and Technology Innovation Committee under Grants No. JCYJ20170306170559215 and No. JCYJ20180302153918689。
文摘In this paper,we propose a hybrid model aiming to map the input noise vector to the label of the generated image by the generative adversarial network(GAN).This model mainly consists of a pre-trained deep convolution generative adversarial network(DCGAN)and a classifier.By using the model,we visualize the distribution of two-dimensional input noise,leading to a specific type of the generated image after each training epoch of GAN.The visualization reveals the distribution feature of the input noise vector and the performance of the generator.With this feature,we try to build a guided generator(GG)with the ability to produce a fake image we need.Two methods are proposed to build GG.One is the most significant noise(MSN)method,and the other utilizes labeled noise.The MSN method can generate images precisely but with less variations.In contrast,the labeled noise method has more variations but is slightly less stable.Finally,we propose a criterion to measure the performance of the generator,which can be used as a loss function to effectively train the network.
基金supported by the fund coded,National Natural Science Fund program(No.11975307)China National Defence Science and Technology Innovation Special Zone Project(19-H863-01-ZT-003-003-12).
文摘Spectrum prediction is one of the new techniques in cognitive radio that predicts changes in the spectrum state and plays a crucial role in improving spectrum sensing performance.Prediction models previously trained in the source band tend to perform poorly in the new target band because of changes in the channel.In addition,cognitive radio devices require dynamic spectrum access,which means that the time to retrain the model in the new band is minimal.To increase the amount of data in the target band,we use the GAN to convert the data of source band into target band.First,we analyze the data differences between bands and calculate FID scores to identify the available bands with the slightest difference from the target predicted band.The original GAN structure is unsuitable for converting spectrum data,and we propose the spectrum data conversion GAN(SDC-GAN).The generator module consists of a convolutional network and an LSTM module that can integrate multiple features of the data and can convert data from the source band to the target band.Finally,we use the generated target band data to train the prediction model.The experimental results validate the effectiveness of the proposed algorithm.
文摘Lithium-ion batteries are key drivers of the renewable energy revolution,bolstered by progress in battery design,modelling,and management.Yet,achieving high-performance battery health prognostics is a significant challenge.With the availability of open data and software,coupled with automated simulations,deep learning has become an integral component of battery health prognostics.We offer a comprehensive overview of potential deep learning techniques specifically designed for modeling and forecasting the dynamics of multiphysics and multiscale battery systems.Following this,we provide a concise summary of publicly available lithium-ion battery test and cycle datasets.By providing illustrative examples,we emphasize the efficacy of five techniques capable of enhancing deep learning for accurate battery state prediction and health-focused management.Each of these techniques offers unique benefits.(1)Transformer models address challenges using self-attention mechanisms and positional encoding methods.(2) Transfer learning improves learning tasks within a target domain by leveraging knowledge from a source domain.(3) Physics-informed learning uses prior knowledge to enhance learning algorithms.(4)Generative adversarial networks(GANs) earn praise for their ability to generate diverse and high-quality outputs,exhibiting outstanding performance with complex datasets.(5) Deep reinforcement learning enables an agent to make optimal decisions through continuous interactions with its environment,thus maximizing cumulative rewards.In this Review,we highlight examples that employ these techniques for battery health prognostics,summarizing both their challenges and opportunities.These methodologies offer promising prospects for researchers and industry professionals,enabling the creation of specialized network architectures that autonomously extract features,especially for long-range spatial-temporal connections across extended timescales.The outcomes could include improved accuracy,faster training,and enhanced generalization.
基金supported in part by the National Natural Science Foundation of China(Grant No.62276274)Shaanxi Natural Science Foundation(Grant No.2023-JC-YB-528)Chinese aeronautical establishment(Grant No.201851U8012)。
文摘The automatic stealth task of military time-sensitive targets plays a crucial role in maintaining national military security and mastering battlefield dynamics in military applications.We propose a novel Military Time-sensitive Targets Stealth Network via Real-time Mask Generation(MTTSNet).According to our knowledge,this is the first technology to automatically remove military targets in real-time from videos.The critical steps of MTTSNet are as follows:First,we designed a real-time mask generation network based on the encoder-decoder framework,combined with the domain expansion structure,to effectively extract mask images.Specifically,the ASPP structure in the encoder could achieve advanced semantic feature fusion.The decoder stacked high-dimensional information with low-dimensional information to obtain an effective mask layer.Subsequently,the domain expansion module guided the adaptive expansion of mask images.Second,a context adversarial generation network based on gated convolution was constructed to achieve background restoration of mask positions in the original image.In addition,our method worked in an end-to-end manner.A particular semantic segmentation dataset for military time-sensitive targets has been constructed,called the Military Time-sensitive Target Masking Dataset(MTMD).The MTMD dataset experiment successfully demonstrated that this method could create a mask that completely occludes the target and that the target could be hidden in real time using this mask.We demonstrated the concealment performance of our proposed method by comparing it to a number of well-known and highly optimized baselines.
