共查询到20条相似文献，搜索用时 26 毫秒
1.
Impressive progress has been made recently in image-to-image translation using generative adversarial networks (GANs). However, existing methods often fail in translating source images with noise to target domain. To address this problem, we joint image-to-image translation with image denoising and propose an enhanced generative adversarial network (EGAN). In particular, built upon pix2pix, we introduce residual blocks in the generator network to capture deeper multi-level information between source and target image distribution. Moreover, a perceptual loss is proposed to enhance the performance of image-to-image translation. As demonstrated through extensive experiments, our proposed EGAN can alleviate effects of noise in source images, and outperform other state-of-the-art methods significantly. Furthermore, we experimentally indicate that the proposed EGAN is also effective when applied to image denoising. 相似文献
2.
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。 相似文献
3.
现有基于循环生成对抗网络的图像生成方法通过引入独立通用的注意力模块,在无匹配图像转换任务中取得了较好的效果,但同时也增加了模型复杂度与训练时间,而且难以关注到图中关键区域的所有细节,图像生成效果仍有提升的空间。针对上述问题,提出一种基于双专用注意力机制引导的循环生成对抗网络（Dual-SAG-CycleGAN）,分别对生成器和判别器采用不同的注意力机制进行引导。首先,提出一种名为SAG（SpecialAttention-mechanismGuided）的专用注意力模块来引导生成器工作,在提升生成图像质量的同时降低网络的复杂度;然后,对判别器采用基于CAM（ClassActivationMapping）的专用注意力机制引导模块,抑制生成器生成无关的噪声;最后,提出背景掩码的循环一致性损失函数,引导生成器生成更加精准的掩码图,更好地辅助图像转换。实验证明,本文方法与现有同类模型相比,网络模型参数量降低近32.8%,训练速度快34.5%,KID与FID最低分别可达1.13和57.54,拥有更高的成像质量。 相似文献
4.
《电子学报:英文版》2024,33(3)
With the rapid development of deep learning,generative adversarial network(GAN)has become a research hotspot in the field of computer vision.GAN has a wide range of applications in image generation.Inspired by GAN,a series of models of Chinese character font generation have been proposed in recent years.In this paper,the latest research progress of Chinese character font generation is analyzed and summarized.GAN and its develop-ment history are summarized.GAN-based methods for Chinese character font generation are clarified as well as their improvements,based on whether the specific elements of Chinese characters are considered.The public datasets used for font generation are summarized in detail,and various application scenarios of font generation are provided.The evaluation metrics of font generation are systematically summarized from both qualitative and quantitative aspects.This paper contributes to the in-depth research on Chinese character font generation and has a positive effect on the inheritance and development of Chinese culture with Chinese characters as its carrier. 相似文献
5.
针对不同波段图像获取代价不同的问题,提出一种基于pix2pix的图像转换方法并进行改进.主要针对生成器和鉴别器两方面进行改进.生成器方面,使用残差结构的生成器替换原来的U-Net生成器以缓解梯度消失问题;引入可变形卷积,提高目标边缘和小目标的生成效果;引入BAM注意力机制,提高了算法对图像中主要目标的特征提取能力以提升生成图像的效果.鉴别器方面:改变PatchGAN中卷积层的层数(原PatchGAN为3层卷积),设置对照实验找到转换效果最好的卷积层数.以可见光图像和红外图像之间的转换为例进行实验.实验结果表明,改进后的算法在生成图像上的均方根误差(MSE)下降了 31.4％、结构相似性(SSIM)提高了 11.2％,可以更好的实现红外图像和可见光图像之间的转换. 相似文献
6.
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. 相似文献
7.
Lue Zhang Hai-Ning Huang Li Yin Bao-Qi Li Di Wu Hao-Ran Liu Xi-Feng Li Yong-Le Xie 《电子科技学刊:英文版》2022,20(3):282-293
The marine biological sonar system evolved in the struggle of nature is far superior to the current artificial sonar. Therefore, the development of bionic underwater concealed detection is of great strategic significance to the military and economy. In this paper, a generative adversarial network(GAN) is trained based on the dolphin vocal sound dataset we constructed, which can achieve unsupervised generation of dolphin vocal sounds with global consistency. Through the analysis of the generated ... 相似文献
8.
《中兴通讯技术（英文版）》2020,18(2):74-82
Crowd counting is a challenging task in computer vision as realistic scenes are always filled with unfavourable factors such as severe occlusions, perspective distortions and diverse distributions. Recent state-of-the-art methods based on convolutional neural network (CNN) weaken these factors via multi-scale feature fusion or optimal feature selection through a front switch-net. L2 regression is used to regress the density map of the crowd, which is known to lead to an average and blurry result, and affects the accuracy of crowd count and position distribution. To tackle these problems, we take full advantage of the application of generative adversarial networks (GANs) in image generation and propose a novel crowd counting model based on conditional GANs to predict high-quality density maps from crowd images. Furthermore, we innovatively put forward a new regularizer so as to help boost the accuracy of processing extremely crowded scenes. Extensive experiments on four major crowd counting datasets are conducted to demonstrate the better performance of the proposed approach compared with recent state-of-the-art methods. 相似文献
9.
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. 相似文献
10.
为了使无人农机在复杂环境的生产过程中及时感知环境信息,避免安全事故发生,本文提出了一种PIE（Poisson Image Editing）和CGAN（Conditional Generative Adversarial Networks）相结合的红外与可见光图像融合算法。首先,利用红外图像及其对应的红外图像显著区域对CGAN网络进行训练;然后,将红外图像输入训练好的网络,即可得到显著区域掩膜;在对其进行形态学优化后进行基于PIE的图像融合;最后,对融合结果进行增强对比度处理。该算法可以实现快速图像融合,满足无人农机实时感知环境的需求,并且该算法保留了可见光图像的细节信息,又能突出红外图像中行人和动物等重要信息,在标准差、信息熵等客观指标上表现良好。 相似文献
11.
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. 相似文献
12.
针对不同谱段图像获取代价不同的问题,提出一种基于生成对抗网络的图像转换方法。转换过程以肉眼可分辨范围内图像轮廓不变为出发点。首先,通过成对的训练数据对生成器和判别器进行交替训练,不断对损失函数进行优化,直到模型达到纳什平衡。然后用测试数据对上述训练好的模型进行检测,查看转换效果,并从主观观察和客观上计算平均绝对误差和均方误差角度评价转换效果。通过上述过程最终实现不同谱段图像之间的转换。其中,生成器借鉴U-Net架构;判别器采用传统卷积神经网络架构;损失函数方面增加L1损失来保证图像转换前后高、低频特征的完整性。以红外图像与可见光图像之间的转换为例进行实验,结果表明,通过本文设计的生成对抗网络,可以较好地实现红外图像与可见光图像之间的转换。 相似文献
13.
针对无监督域自适应行人重识别中存在的聚类不准确导致网络识别准确率低的问题,提出一种基于生成对抗网络的无监督域自适应行人重识别方法。首先通过在池化层后使用批量归一化层、删除一层全连接层和使用Adam优化器等方法优化CNN模型;然后基于最小错误率贝叶斯决策理论分析聚类错误率和选择聚类关键参数;最后利用生成对抗网络调整聚类,有效提升了无监督域自适应行人重识别的识别准确率。在源域Market-1501和目标域DukeMTMC-reID下进行实验,mAP和Rank-1分别达到了53.7%和71.6%。 相似文献
14.
现有的层级式文本生成图像的方法在初始图像生成阶段仅使用上采样进行特征提取,上采样过程本质是卷积运算,卷积运算的局限性会造成全局信息被忽略并且远程语义无法交互。虽然已经有方法在模型中加入自注意力机制,但依然存在图像细节缺失、图像结构性错误等问题。针对上述存在的问题,提出一种基于自监督注意和图像特征融合的生成对抗网络模型SAF-GAN。将基于ContNet的自监督模块加入到初始特征生成阶段,利用注意机制进行图像特征之间的自主映射学习,通过特征的上下文关系引导动态注意矩阵,实现上下文挖掘和自注意学习的高度结合,提高低分辨率图像特征的生成效果,后续通过不同阶段网络的交替训练实现高分辨率图像的细化生成。同时加入了特征融合增强模块,通过将模型上一阶段的低分辨率特征与当前阶段的特征进行融合,生成网络可以充分利用低层特征的高语义信息和高层特征的高分辨率信息,更加保证了不同分辨率特征图的语义一致性,从而实现高分辨率的逼真的图像生成。实验结果表明,相较于基准模型（AttnGAN）,SAF-GAN模型在IS和FID指标上均有改善,在CUB数据集上的IS分数提升了0.31,FID指标降低了3.45;在COCO数据集上的IS分数提升了2.68,FID指标降低了5.18。SAF-GAN模型能够有效生成更加真实的图像,证明了该方法的有效性。 相似文献
15.
小样本条件下基于数据增强和WACGAN的雷达目标识别算法 总被引：1，自引：0，他引：1
目前小样本条件下高分辨距离像雷达目标识别算法存在识别率较低、识别率稳定度较差等问题,对此,本文提出了基于数据增强和加权辅助分类生成对抗网络(Weighted Auxiliary Classifier Generative Adversarial Networks,WACGAN)的雷达目标识别算法.该算法首先根据雷达目标散射特性,通过时间镜像数据增强方法扩充数据集,然后将扩充数据集输入WACGAN,通过自动选择高质量的生成样本,使判别器在标签样本监督学习的基础上得到进一步优化,最后直接利用判别器实现对雷达目标的有效识别.仿真实验结果表明,本文算法在不增加识别时间的基础上,有效提高了小样本条件下对雷达目标的识别率和识别稳定度. 相似文献
16.
为了提高生成远程光电容积脉搏波描记法(remote Photoplethysmography,rPPG)信号的波形规律性,降低心率计算难度,提出了一种标准化rPPG的信号生成方法.将人脸视频输入到生成对抗网络的生成器中,生成器通过有标签数据进行监督训练,预测得到人脸视频中蕴含的rPPG信号.为了进一步优化生成器的预测结果,使用数学建模方法生成标准的rPPG信号,并将其与生成器预测的信号同时输入至判别器中进行对抗学习,不断优化生成器参数,使得生成器能够学习标准信号的波形分布.这样,生成器预测的信号波形在形态上更接近于真实rPPG信号的波形分布,从而有利于后续心率计算.在不同数据集上进行的实验结果表明,该方法可以显著提高预测的准确性,且拥有更高的信噪比. 相似文献
17.
A hybrid quantum–classical approach to model continuous classical probability distributions using a variational quantum circuit is proposed. The architecture of this quantum generator consists of a quantum circuit that encodes a classical random variable into a quantum state and a parameterized quantum circuit trained to mimic the target distribution. The model allows for easy interfacing with a classical function, such as a neural network, and is trained using an adversarial learning approach. It is shown that the quantum generator is able to learn using either a classical neural network or a variational quantum circuit as the discriminator model. This implementation takes advantage of automatic differentiation tools to perform the optimization of the variational circuits employed. The framework presented here for the design and implementation of the variational quantum generators can serve as a blueprint for designing hybrid quantum–classical models for other machine learning tasks. 相似文献
18.
19.
针对循环生成对抗网络(Cycle Generative Adversarial Networks, CycleGAN)在浑浊水体图像增强中存在质量差和速度慢的问题,该文提出一种可扩展、可选择和轻量化的特征提取单元BSDK (Bottleneck Selective Dilated Kernel),并利用BSDK设计了一个新的生成器网络BSDKNet。与此同时,提出一种多尺度损失函数MLF(Multi-scale Loss Function)。在自建的浑浊水体图像增强数据集TC(Turbid and Clear)上,该文BM-CycleGAN比原始CycleGAN的精度提升3.27%,生成器网络参数降低4.15MB,运算时间减少0.107s。实验结果表明BM-CycleGAN适合浑浊水体图像增强任务。 相似文献
20.
The World Health Organization provides guidelines for managing the particulate matter (PM) level because a higher PM level represents a threat to human health. To manage the PM level, a procedure for measuring the PM value is first needed. We use a PM sensor that collects the PM level by laser-based light scattering (LLS) method because it is more cost effective than a beta attenuation monitor-based sensor or tapered element oscillating microbalance-based sensor. However, an LLS-based sensor has a higher probability of malfunctioning than the higher cost sensors. In this paper, we regard the overall malfunctioning, including strange value collection or missing collection data as anomalies, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that we call the hypothesis pruning generative adversarial network (HP-GAN). Through comparative experiments, we achieve AUROC and AUPRC values of 0.948 and 0.967, respectively, in the detection of anomalies in LLS-based PM measuring sensors. We conclude that our HP-GAN is a cutting-edge model for anomaly detection. 相似文献
