基于空间特征的生成对抗网络数据生成方法

传统的生成对抗网络(GAN)在特征图较大的情况下，忽略了原始特征的表示和结构信息，并且生成图像的像素之间缺乏远距离相关性，从而导致生成的图像质量较低。为了进一步提高生成图像的质量，该文提出一种基于空间特征的生成对抗网络数据生成方法(SF-GAN)。该方法首先将空间金字塔网络加入生成器和判别器，来更好地捕捉图像的边缘等重要的描述信息；然后将生成器和判别器进行特征加强，来建模像素之间的远距离相关性。使用CelebA,SVHN,CIFAR-10等小规模数据集进行实验，通过定性和盗梦空间得分(IS)、弗雷歇距离(FID)定量评估证明了所提方法相比梯度惩罚生成对抗网络(WGAN-GP)、自注意力生成对抗网络(SAGAN)能使生成的图像具有更高的质量。并且通过实验证明了该方法生成的数据能够进一步提升分类模型的训练效果。     

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.     

基于深度生成对抗网络的海杂波数据增强方法

海杂波数据稀缺,获取海杂波数据成本高、周期长,极大地限制了海杂波特性研究及海洋遥感应用。该文主要研究了基于深度生成性对抗网络(GAN)的海杂波数据生成方法,通过扩展传统的GAN框架,形成了1维海杂波数据生成和鉴别模型,基于实测海杂波数据集,进行对抗网络生成和鉴别模型训练,分析了生成模型所生成的海杂波数据的幅度分布特性和时间、空间相关性。基于实测数据验证了该方法能够生成更多、更多样、与真实海杂波数据分布相近的海杂波数据。     

基于对抗式生成网络的农作物病虫害图像扩充

本文提出一种基于深度卷积对抗式生成网络(Deep convolutional GAN,DCGAN)的农作物病虫害图像生成方法,利用卷积神经网络强大的特征提取能力,提高生成网络的学习效果,生成大量接近真实数据的病虫害图像。实验结果表明,该方法能有效解决病虫害图像数据不足的问题。     

基于生成对抗网络的盾构隧道渗漏水检测

渗漏水是盾构隧道安全危害最大的病害之一,对盾构隧道渗漏水快速精准的检测,是有效控制及整治盾构隧道渗漏水的基础。现有的渗漏水检测方法在自动化程度方面均取得一定的成效,但存在数据采集效率低、现场采集环境要求高、训练数据样本量大等问题。针对上述问题,文章将移动LiDAR采集的盾构隧道强度图像作为数据源,提出了基于生成对抗网络的盾构隧道渗漏水检测方法,从现有的生成对抗网络V GAN模型出发,在标注少量样本的基础上,建立了Dense块作为编码器,残差块作为解码器的Unet模型作为生成器网络,运用改进的深度残差Unet(Improve ResUnet)作为判别器网络,组成DRUnet IRUnet GAN生成对抗网络用于盾构隧道LiDAR强度图像渗漏水检测。实验结果表明,当输入500张、200张、100张少量样本时,文章构建的DRUnet IRUnet GAN生成对抗网络能够达到优于V GAN的盾构隧道强度图像渗漏水检测效果,表明了所改进的网络具有良好的性能。     

基于深度生成对抗网络的海杂波数据增强方法

海杂波数据稀缺,获取海杂波数据成本高、周期长,极大地限制了海杂波特性研究及海洋遥感应用.该文主要研究了基于深度生成性对抗网络(GAN)的海杂波数据生成方法,通过扩展传统的GAN框架,形成了1维海杂波数据生成和鉴别模型,基于实测海杂波数据集,进行对抗网络生成和鉴别模型训练,分析了生成模型所生成的海杂波数据的幅度分布特性和时间、空间相关性.基于实测数据验证了该方法能够生成更多、更多样、与真实海杂波数据分布相近的海杂波数据.     

基于半监督学习生成对抗网络的人脸还原算法研究

基于大量训练样本生成高置信度图像的生成对抗网络研究已经取得一些成果,但是现有的研究只针对已知训练样本进行图像生成,而未将训练的参数用于训练样本之外的图像生成。该文设计了一种改进的生成对抗网络模型,在已有网络的基础上增加一个还原层,使得测试图像可以通过改进的对抗网络生成对应的高置信度图像。实验结果表明,改进的生成对抗网络参数可以应用到训练集之外的普通样本。同时本文改进了生成模型的损失算法,极大地缩短了网络的收敛时间。     

基于对抗生成网络的纹理合成方法

纹理合成是计算机图形学、计算机视觉和图像处理领域的研究热点之一。传统的纹理合成方法往往通过提取有效的特征样式或统计量并在该特征信息的约束下生成随机图像来实现。对抗生成网络作为一种较新的深度网络形式,通过生成器和判别器的对抗训练能够随机生成与观测数据具有相同分布的新数据。鉴于此,提出了一种基于对抗生成网络的纹理合成方法。该算法的优点是不需要经过多次迭代就能够生成更真实纹理图像,且生成图像在视觉上与观测纹理图像一致的同时具有一定随机性。一系列针对随机纹理和结构性纹理的合成实验验证了该算法的有效性。     

基于图像纹理渲染的智能绘画效果生成算法设计

针对计算机智能绘画算法模型在纹理细节处理上效果不佳的问题,文中提出了一种基于图像纹理渲染的智能绘画算法。该算法以生成对抗神经网络为基础,设计了分层融合生成对抗神经网络架构。并利用结构GAN生成了一幅具有图像结构线条的图片,且将输出的图像与均匀分布的噪声作为纹理GAN的输入数据。通过纹理GAN融合图像的结构与纹理特征,进而渲染生成逼真的图像。测试结果表明,利用该种算法绘制出的素描图像纹理清晰、形象逼真,且在定量分析中IS指标达到了2.31,高于其他对比算法。     

基于改进的U-Net生成对抗网络的图像翻译算法

针对传统生成对抗网络(Generative Adversarial Networks,GAN)在图像翻译过程中生成图像的轮廓、纹理等特征丢失以及造成图像翻译效果不佳的问题,提出了基于改进U-Net模型的生成对抗网络图像翻译算法。首先,实验研究Pix2Pix生成对抗网络优化算法、学习率以及迭代次数对图像翻译效果的影响,确定生成对抗网络模型参数与优化方法;其次,通过增加反卷积跳跃连接的重复次数增强特征的表达能力;最后,在CUFS人脸数据库上进行实验确定模型参数。实验表明,反卷积跳跃连接的重复次数为5次时,图像翻译的用户调研满意评价指标达到42%,图像翻译的质量达到最优。     

改进生成式对抗网络的图像数据集增强算法

针对现有深度学习中图像数据集缺乏的问题,提出了一种基于深度卷积生成式对抗网络(Deep Convolutional Generative Adversarial Network, DCGAN)的图像数据集增强算法。该算法对DCGAN网络进行改进,首先在不过多增加计算量的前提下改进现有的激活函数,增强生成特征的丰富性与多样性;然后通过引入相对判别器有效缓解模式坍塌现象,从而提升模型稳定性;最后在现有生成器结构中引入残差块,获得相对高分辨率的生成图像。实验结果表明,将所提方法应用在MNIST、SAR和医学血细胞数据集上,图像数据增强效果与未改进的DCGAN网络相比显著提升。     

Stable self-attention adversarial learning for semi-supervised semantic image segmentation

The application of adversarial learning for semi-supervised semantic image segmentation based on convolutional neural networks can effectively reduce the number of manually generated labels required in the training process. However, the convolution operator of the generator in the generative adversarial network (GAN) has a local receptive field, so that the long-range dependencies between different image regions can only be modeled after passing through multiple convolutional layers. The present work addresses this issue by introducing a self-attention mechanism in the generator of the GAN to effectively account for relationships between widely separated spatial regions of the input image with supervision based on pixel-level ground truth data. In addition, the adjustment of the discriminator has been demonstrated to affect the stability of GAN training performance. This is addressed by applying spectral normalization to the GAN discriminator during the training process. Our method has better performance than existing full/semi-supervised semantic image segmentation techniques.     

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.     

面向SAR图像处理的生成式对抗网络应用综述

针对缺少合成孔径雷达(Synthetic Aperture Radar,SAR)目标图像数据导致的识别网络难以训练的问题,总结了现有的基于深度学习方法的解决方案。归纳了现阶段生成式对抗网络(Generative Adversarial Network,GAN)的发展情况,以及主要的衍生模型及其特点与优势。综述了GAN在SAR图像生成与风格迁移两方面的应用情况,并合理分析了应用中的技术难点和问题。最后结合深度学习的发展趋势,展望了GAN在SAR智能解译方面的应用。     

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.     

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.     

A no-reference perceptual image quality assessment database for learned image codecs

The drastic growth of research in image compression, especially deep learning-based image compression techniques, poses new challenges to objective image quality assessment (IQA). Typical artifacts encountered in the emerging image codecs are significantly different from that produced by traditional block-based codecs, leading to inapplicability of the existing objective IQA algorithms. Towards advancing the development of objective IQA algorithms for recent compression artifacts, we built a learning-based compressed image quality assessment (LCIQA) database involving traditional block-based image codecs, hybrid neural network based image codecs, convolutional neural network based and generative adversarial network (GAN) based end-to-end optimized image coding approaches. Our study confirms the statistical difference and human perception difference between reconstructions of learned compression and traditional block-based compression. We propose a two-step deep learning model for learning-based compressed image quality assessment. Extensive experiments on LCIQA database demonstrate that our proposed model performs better than other counterparts on learning-based compressed images, especially on GAN compressed images, and achieves competitive performance to the state-of-the-art IQA metrics on traditional compressed images.     

基于自监督对比学习的深度神经网络对抗鲁棒性提升

基于深度神经网络的多源图像内容自动分析与目标识别方法近年来不断取得新的突破,并逐步在智能安防、医疗影像辅助诊断和自动驾驶等多个领域得到广泛部署。然而深度神经网络的对抗脆弱性给其在安全敏感领域的部署带来巨大安全隐患。对抗鲁棒性的有效提升方法是采用最大化网络损失的对抗样本重训练深度网络,但是现有的对抗训练过程生成对抗样本时需要类别标记信息,并且会大大降低无攻击数据集上的泛化性能。本文提出一种基于自监督对比学习的深度神经网络对抗鲁棒性提升方法,充分利用大量存在的无标记数据改善模型在对抗场景中的预测稳定性和泛化性。采用孪生网络架构,最大化训练样本与其无监督对抗样本间的多隐层表征相似性,增强模型的内在鲁棒性。本文所提方法可以用于预训练模型的鲁棒性提升,也可以与对抗训练相结合最大化模型的“预训练+微调”鲁棒性,在遥感图像场景分类数据集上的实验结果证明了所提方法的有效性和灵活性。