基于生成对抗网络的SAR图像降噪模型

合成孔径雷达(SAR)是相干成像系统,生成的图像经常会被相干斑噪声污染,继而造成了SAR图像在后续分割、识别中准确率低的问题。针对图像被污染问题,设计了一种结合生成对抗网络(GAN)与残差网络(ResNet)的SAR图像降噪网络模型Re-GAN,其中,GAN中的生成器加入了ResNet中的残差块以增强对SAR图像降噪的能力,模型中的组合损失函数在降噪时可以更好地保留图像细节。在MATAR数据集上,Re-GAN分别与BM3D算法、小波降噪算法进行比较,实验结果证明,Re-GAN在视觉效果和定量分析方面都具有良好的性能。     

基于改进CycleGAN的ISAR图像超分辨方法

图像超分辨是解决ISAR欺骗干扰中由于模型样本不完备导致难以对大带宽ISAR实现高逼真假目标模拟的重要手段。利用生成对抗网络（GAN）可通过端到端映射实现ISAR图像的超分辨,然而,当测试输入样本与训练输入样本分辨率差异较大时,超分辨图像中会出现伪散射点从而导致目标失真。考虑到循环生成对抗网络（CycleGAN）对输入样本差异适应性较好,本文提出了一种基于改进CycleGAN的ISAR欺骗干扰超分辨样本生成方法,分别从损失函数、优化过程、判别器结构三方面对CycleGAN网络结构进行改进,加快了网络的收敛速度,同时对于输入分辨率差异较大的ISAR图像泛化性能更好。利用暗室测量数据验证了所提方法的有效性,与GAN方法相比,对于训练输入样本分辨率差异较大的测试输入样本,生成的超分辨样本散射点位置与真实数据具有更好的匹配效果。     

面向医学图像生成的鲁棒条件生成对抗网络

医学图像生成是计算机辅助诊断技术的关键组成,具有广泛的应用场景.当前基于生成对抗网络的端对端学习模型,依靠生成器和判别器两者对抗训练,获取真实数据的概率分布,从而指导图像生成.但标注有限的医学图像及其高分辨率特点,加大了模型训练难度,影响图像生成质量;同时,模型未纳入数据扰动因素,鲁棒性有限,容易被恶意攻击.为此,本文提出一个基于鲁棒条件生成对抗网络的医学图像生成模型——MiSrc-GAN.该模型包括精度渐进生成器、多尺度判别器以及对抗样本配对构造模块,有效融合GAN框架和对抗样本,改善判别器鲁棒性,有利于学习原始图像与待生成图像的联合概率分布.在真实数据集CSC和REFUGE上的实验表明,MiSrc-GAN生成的图像质量优于现有模型.     

基于多通道GAN的图像去噪算法

针对图像采集和传输过程中所产生噪声导致后续图像处理能力下降的问题,提出基于生成对抗网络(GAN)的多通道图像去噪算法。所提算法将含噪彩色图像分离为RGB三通道,各通道基于具有相同架构的端到端可训练的GAN实现去噪。GAN生成网络基于U-net衍生网络以及残差块构建,从而可参考低级特征信息以有效提取深度特征进而避免丢失细节信息;判别网络则基于全卷积网络构造,因而可获得像素级分类从而提升判别精确性。此外,为改善去噪能力且尽可能保留图像细节信息,所构建去噪网络基于对抗损失、视觉感知损失和均方误差损失这3类损失度量构建复合损失函数。最后,利用算术平均方法融合三通道输出信息以获得最终去噪图像。实验结果表明,与主流算法相比,所提算法可有效去除图像噪声,且可较好地恢复原始图像细节。     

利用残差生成对抗网络的高光谱图像分类

针对高光谱图像分类过程中存在的标记样本需求量大和分类精度要求高等问题,提出了一种利用残差生成对抗网络（GAN）的高光谱图像分类方法。该方法以生成对抗网络为基础,使用包含上采样层和卷积层构成的8层残差网络替换生成器的反卷积层网络结构,提高数据的生成能力,使用34层残差卷积网络替换判别器的卷积层网络结构,提高特征提取能力。以Pavia University、Salinas及Indian Pines数据集为实验数据,将所提方法与GAN、CAE-SVM、2DCNN、3DCNN、ResNet进行了比较。实验结果表明,所提方法在总体分类精度、平均分类精度和Kappa系数上均有显著提高,其中总体分类精度在Indian Pines数据集上达到了98.84%,较对比方法分别提高了2.99个百分点、22.03个百分点、12.91个百分点、4.99个百分点、1.79个百分点。所提方法在网络中加入残差结构,增强了浅层网络与深层网络的信息交流,可提取高光谱图像的深层次特征,提高了高光谱图像分类的精度。     

基于改进超分辨率生成对抗网络的图像重建算法

针对现有基于像素损失的超分辨率图像重建算法对纹理等高频细节的重建效果差问题,提出了一种基于改进超分辨率生成对抗网络(SRGAN)的图像重建算法.首先,去除了生成器中的批归一化层,并结合多级残差网络和密集连接,用残差套残差密集块提高了网络提取特征的能力.然后,结合均方误差与感知损失作为指导生成器训练的损失函数,既保留了图...     

生成对抗网络在医学图像中的应用研究

生成对抗网络(generative adversarial network,GAN)作为深度学习下无监督学习的典型方法,使用深度学习的计算机辅助诊断系统目前已经覆盖病灶检测、病理诊断、放疗规划和术后预测等各临床阶段,在医学图像领域取得了许多显著的成果.首先介绍了医学图像领域存在的基本问题,并简单介绍了生成对抗网络模型的...     

基于谱约束的生成对抗网络图像数据生成研究

数据匮乏是深度学习面临的一大难题。利用生成对抗网络(GAN)能够基于语义生成新的图像数据这一特性,提出一种基于谱约束的生成对抗网络图像数据生成方法,该方法针对卷积生成对抗网络模型易崩溃不收敛的问题,从每层神经网络的参数矩阵W的谱范数角度出发,引入谱范数归一化网络参数矩阵,将网络梯度限制在固定范围内,减缓判别网络收敛速度,从而提高GAN的训练稳定性。实验表明,通过该方法生成的数据相比原始GAN以及DCGAN、WGAN等生成的图像样本数据在图像识别网络中具有更高的准确率,能够对少量样本数据进行有效扩充。     

SEGQM:一种基于SE-ResNet的DCGAN质量评价模型

生成对抗网络(Generative Adversarial Network,GAN)通过对抗学习获得生成数据的能力.它的生成图像与真实图像没有绝对的对应关系,因此传统方法很难具体量化生成图像的视觉质量和多样性.通过对GQI进行改进,利用SE-ResNet分类,提出了一种能够定量评价GAN生成图像真实性和多样性的评价模型...     

基于生成对抗网络的遥感图像超分辨率重建改进算法

为了获取包含更多高频感知信息与纹理细节信息的遥感重建图像，并解决超分辨率重建算法训练难和重建图像细节缺失的问题，提出一种融合多尺度感受野模块的生成对抗网络（GAN）遥感图像超分辨率重建算法。首先，使用多尺度卷积级联增强全局特征获取、去除GAN中的归一化层，提升网络训练效率去除伪影并降低计算复杂度；其次，利用多尺度感受野模块与密集残差模块作为生成网络的细节特征提取模块，提升网络重建质量获取更多细节纹理信息；最后，结合Charbonnier损失函数与全变分损失函数提升网络训练稳定性加速收敛。实验结果表明，所提算法在Kaggle、WHURS19、AID数据集上的平均检测结果较超分辨率GAN在峰值信噪比、结构相似性、特征相似性等方面分别高出约1.65 dB、约0.040(5.2%)、约0.010(1.1%)。     

Detection of GAN generated image using color gradient representation

With the development of generative adversarial network (GANs) technology, the technology of GAN generates images has evolved dramatically. Distinguishing these GAN generated images is challenging for the human eye. Moreover, the GAN generated fake images may cause some behaviors that endanger society and bring great security problems to society. Research on GAN generated image detection is still in the exploratory stage and many challenges remain. Motivated by the above problem, we propose a novel GAN image detection method based on color gradient analysis. We consider the difference in color information between real images and GAN generated images in multiple color spaces, and combined the gradient information and the directional texture information of the generated images to extract the gradient texture features for GAN generated images detection. Experimental results on PGGAN and StyleGAN2 datasets demonstrate that the proposed method achieves good performance, and is robust to other various perturbation attacks.     

GAN-based data augmentation of prohibited item X-ray images in security inspection

Convolutional neural networks (CNNs) based methods for automatic discriminant of prohibited items in X-ray images attract attention increasingly. However, it is difficult to train a reliable CNN model using the available X-ray security image databases, since they are not enough in sample quantity and diversity. Recently, generative adversarial network (GAN) has been widely used in image generation and regarded as a power model for data augmentation. In this paper, we propose a data augmentation method for X-ray prohibited item images based on GAN. First, the network structure and loss function of the self-attention generative adversarial network (SAGAN) are improved to generate the realistic X-ray prohibited item images. Then, the images generated by our model are evaluated using GAN-train and GAN-test. Experimental results of GAN-train and GAN-test are 99.91% and 98.82% respectively. It implies that our model can enlarge the X-ray prohibited item image database effectively.     

一种基于U-Net生成对抗网络的低照度图像增强方法

在低照度环境下采集的图像具有低信噪比、低对比度及低分辨率等特点,导致图像难以识别利用.为了提升低照度图像的质量,本文提出一种基于U-Net生成对抗网络的低照度图像增强方法.首先利用U-Net框架实现生成对抗网络中的生成网络,然后利用该生成对抗网络学习从低照度图像到正常照度图像的特征映射,最终实现低照度图像的照度增强.实验结果表明,与主流算法相比,本文提出的方法能够更有效的提升低照度图像的亮度与对比度.     

Fault detection and diagnosis method for heterogeneous wireless network based on GAN

Aiming at the problem that in the process of network fault detection and diagnosis,how to train the precise fault diagnosis and detection model based on small data volume,a fault diagnosis and detection algorithm based on generative adversarial networks (GAN) for heterogeneous wireless networks was proposed.Firstly,the common network fault sources in heterogeneous wireless network environment was analyzed,and a large number of reliable data sets was obtained based on a small amount of network fault samples through GAN algorithm.Then,the extreme gradient boosting (XGBoost) algorithm was used to select the optimal feature combination of input parameters in the fault detection stage and completed fault diagnosis and detection based on these data.Simulation results show that the algorithm can achieve more accurate and efficient fault detection and diagnosis for heterogeneous wireless networks,with an accuracy of 98.18%.     

Advances in generative adversarial network

Generative adversarial network (GAN) have swiftly become the focus of considerable research in generative models soon after its emergence,whose academic research and industry applications have yielded a stream of further progress along with the remarkable achievements of deep learning.A broad survey of the recent advances in generative adversarial network was provided.Firstly,the research background and motivation of GAN was introduced.Then the recent theoretical advances of GAN on modeling,architectures,training and evaluation metrics were reviewed.Its state-of-the-art applications and the extensively used open source tools for GAN were introduced.Finally,issues that require urgent solutions and works that deserve further investigation were discussed.     

基于DAWGAN-GP的磁共振图像重构方法研究

本文提出了一种基于改进Wasserstein生成式对抗网络（De-aliasing Wasserstein Generative Adversarial Network with Gradient Penalty,DAWGAN-GP）的磁共振图像重构算法,该方法利用Wasserstein生成式对抗网络代替传统的生成式对抗网络,并结合梯度惩罚的方法提高训练速度,解决WGAN收敛缓慢问题.此外,为了有更好的重构效果,我们将感知损失,像素损失和频域损失引入至损失函数中进行网络训练.实验结果表明,对比现有的基于深度学习的磁共振图像重构算法,基于DAWGAN-GP的磁共振图像重构方法具有更好的重构效果,可获得更高的峰值信噪比（Peak Signal to Noise Ratio,PSNR）和更好的结构相似性（Structural Similarity Index Measure,SSIM）.     

Exploration of the Relation between Input Noise and Generated Image in Generative Adversarial Networks

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.     

Generative adversarial networks for hyperspectral image spatial super-resolution

It is becoming increasingly easier to obtain more abundant supplies for hyperspectral images ( HSIs). Despite this, achieving high resolution is still critical. In this paper, a method named hyperspectral images super-resolution generative adversarial network ( HSI-RGAN ) is proposed to enhance the spatial resolution of HSI without decreasing its spectral resolution. Different from existing methods with the same purpose, which are based on convolutional neural networks ( CNNs) and driven by a pixel-level loss function, the new generative adversarial network (GAN) has a redesigned framework and a targeted loss function. Specifically, the discriminator uses the structure of the relativistic discriminator, which provides feedback on how much the generated HSI looks like the ground truth. The generator achieves more authentic details and textures by removing the place of the pooling layer and the batch normalization layer and presenting smaller filter size and two-step upsampling layers. Furthermore, the loss function is improved to specially take spectral distinctions into account to avoid artifacts and minimize potential spectral distortion, which may be introduced by neural networks. Furthermore, pre-training with the visual geometry group (VGG) network helps the entire model to initialize more easily. Benefiting from these changes, the proposed method obtains significant advantages compared to the original GAN. Experimental results also reveal that the proposed method performs better than several state-of-the-art methods.     

High-quality face image generation based on generative adversarial networks

Conventional face image generation using generative adversarial networks (GAN) is limited by the quality of generated images since generator and discriminator use the same backpropagation network. In this paper, we discuss algorithms that can improve the quality of generated images, that is, high-quality face image generation. In order to achieve stability of network, we replace MLP with convolutional neural network (CNN) and remove pooling layers. We conduct comprehensive experiments on LFW, CelebA datasets and experimental results show the effectiveness of our proposed method.