共查询到20条相似文献，搜索用时 15 毫秒
1.
Existing face aging (FA) approaches usually concentrate on a universal aging pattern, and produce restricted aging faces from one-to-one mapping. However, the diversity of living environments impact individuals differently in their oldness. To simulate various aging effects, we propose a multimodal FA framework based on face disentanglement technique of age-specific and age-irrelevant information. A Variational Autoencoder (VAE)-based encoder is designed to represent the distribution of the age-specific attributes. To capture the age-irrelevant features, a cycle-consistency loss of unpaired faces is utilized among various age spans. The extensive experimental results demonstrate that the sampled age-specific codes along with an age-irrelevant feature make the multimodal FA diverse and realistic. 相似文献
2.
3.
In this paper, we proposed a semi-supervised common representation learning method with GAN-based Asymmetric Transfer Network (GATN) for cross modality retrieval. GATN utilizes the asymmetric pipeline to guarantee the semantic consistency and adopt (Generative Adversarial Network) GAN to fit the distributions of different modalities. Specifically, the common representation learning across modalities includes two stages: (1) the first stage, GATN trains source mapping network to learn the semantic representation of text modality by supervised method; and (2) the second stage, GAN-based unsupervised modality transfer method is proposed to guide the training of target mapping network, which includes generative network (target mapping network) and discriminative network. Experimental results on three widely-used benchmarks show that GATN have achieved better performance comparing with several existing state-of-the-art methods. 相似文献
5.
In this paper, we present a novel deep generative facial parts swapping method: parts-swapping generative adversarial network (PSGAN). PSGAN independently handles facial parts, such as eyes (left eye and right eye), nose, mouth and jaw, which achieves facial parts swapping by replacing the target facial parts with source facial parts and reconstructing the entire face image with these parts. By separately modeling the facial parts in the form of region inpainting, the proposed method can successfully achieve highly photorealistic face swapping results, enabling users to freely manipulate facial parts. In addition, the proposed method is able to perform jaw editing based on sketch guidance information. Experimental results on the CelebA dataset suggest that our method achieves superior performance for facial parts swapping and provides higher user control flexibility. 相似文献
6.
Translating multiple real-world source images to a single prototypical image is a challenging problem. Notably, these source images belong to unseen categories that did not exist during model training. We address this problem by proposing an adaptive adversarial prototype network (AAPN) and enhancing existing one-shot classification techniques. To overcome the limitations that traditional works cannot extract samples from novel categories, our method tends to solve the image translation task of unseen categories through a meta-learner. We train the model in an adversarial learning manner and introduce a style encoder to guide the model with an initial target style. The encoded style latent code enhances the performance of the network with conditional target style images. The AAPN outperforms the state-of-the-art methods in one-shot classification of brand logo dataset and achieves the competitive accuracy in the traffic sign dataset. Additionally, our model improves the visual quality of the reconstructed prototypes in unseen categories. Based on the qualitative and quantitative analysis, the effectiveness of our model for few-shot classification and generation is demonstrated. 相似文献
7.
In the field of affective computing (AC), coarse-grained AC has been developed and widely applied in many fields. Electroencephalogram (EEG) signals contain abundant emotional information. However, it is difficult to develop fine-grained AC due to the lack of fine-grained labeling data and suitable visualization methods for EEG data with fine labels. To achieve a fine mapping of EEG data directly to facial images, we propose a conditional generative adversarial network (cGAN) to establish the relationship between EEG data associated with emotions, a coarse label, and a facial expression image in this study. In addition, a corresponding training strategy is also proposed to realize the fine-grained estimation and visualization of EEG-based emotion. The experiments prove the reasonableness of the proposed method for the generation of fine-grained facial expressions. The image entropy of the generated image indicates that the proposed method can provide a satisfactory visualization of fine-grained facial expressions. 相似文献
8.
武铭泽;刘庆华;欧阳缮 《电波科学学报》2025,40(1):141-154
在探地雷达(ground penetrating radar, GPR)应用中,反演成像是解译GPR数据信息的关键技术。现有基于深度学习的GPR图像反演技术大多应用于地下均匀介质的理想环境,然而真实环境中采集到的数据通常包含复杂的噪声与杂波信号,对反演精度有很大影响。针对这一问题,本文提出了一种基于生成对抗网络(generative adversarial network, GAN)的两阶段GPR图像反演网络TSInvNet,以重构真实环境中地下目标的位置分布。该方法先将GPR B-scan图像使用改进的空间自适应归一化(spatially-adaptive normalization, SPADE)生成器的去噪网络TSInvNet1进行处理后,接着送入引入置换注意力(shuffle attention, SA)模型的反演网络TSInvNet2进行反演。在模拟数据与真实数据上的实验结果表明,TSInvNet能够根据GPR B-scan图像准确反演出地下目标的位置,在具有复杂噪声与多目标情况下的反演应用中具有强鲁棒性和精确反演性能。 相似文献
9.
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
10.
胃肠镜检查是目前临床上检查和诊断消化道疾病最重要的途径,内窥镜图像的运动模糊会对医生诊断和机器辅助诊断造成干扰。现有的去模糊网络由于缺乏对结构信息的关注,在处理内窥镜图像时普遍存在着伪影和结构变形的问题。为解决这一问题,提高胃镜图像质量,该文提出一种基于梯度指导的生成对抗网络,网络以多尺度残差网络(Res2net)结构作为基础模块,包含图像信息支路和梯度支路两个相互交互的支路,通过梯度支路指导图像去模糊重建,从而更好地保留图像结构信息,消除伪影、缓解结构变形;设计了类轻量化预处理网络来纠正过度模糊,提高训练效率。在传统胃镜和胶囊胃镜数据集上分别进行了实验,实验结果表明,该算法的峰值信噪比(PSNR)和结构相似度(SSIM)指标均优于对比算法,且复原后的视觉效果更佳,无明显伪影和结构变形。 相似文献
11.
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
13.
《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
14.
15.
针对人脸超分辨率算法中图像失真大、缺乏细节特征等问题,提出了一种基于先验知识的人脸超分辨率重建模型。通过在超分网络中加入纹理辅助分支,为重建过程提供额外纹理结构先验,以生成精细的面部纹理,恢复高分辨率纹理图。同时引入级联叠加模块对纹理辅助分支进行反馈。设计特征融合模块,将纹理特征图与超分分支特征图融合,获得更好的纹理细节;将纹理损失融入损失函数,以提高网络恢复纹理细节的能力。4倍放大因子下,该方法的峰值信噪比(Peak Signal-to-Noise Ratio, PSNR)、结构相似性指数(Structural Similarity Index, SSIM)比现有方法至少提升1.082 5 dB和0.036,无参考图像质量评价(Natural Image Quality Evaluator, NIQE)至少降低1.690 2;8倍放大因子下,该方法的PSNR与SSIM值分别至少提升0.787 5 dB和0.046 85,NIQE值最小降低3.92。 相似文献
16.
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。 相似文献
17.
Despite the notable successes of Generative adversarial networks (GANs) achieved to date, applying them to real-world problems still poses significant challenges. In real traffic surveillance scenarios, for the task of generating images of multiple color of truck heads and cars without changing textures and license plates, conditional image generation hardly manipulate the generated images by the color attribute. Image style transfer methods inevitably produce color smearing. Even state-of-the-art methods of disentangled representation learning (e.g. MixNMatch) cannot disentangle colors individually, ensuring that irrelevant factors, such as texture remain the same. To solve this problem, we present an approach called Multi-ColorGAN based on memory-augmented networks for multi-color real vehicle coloring/generation with limited data. In particular, our model could filter out unwanted color changes in specific areas with a simple but effective method called Fusion Module, and generate more natural color images. Experiments on three vehicle image benchmarks and a new truck image dataset are conducted to evaluate the proposed Multi-ColorGAN compared to state-of-the-art. 相似文献
18.
19.
Zeyi LI;Pan WANG;Zixuan WANG 《电子学报:英文版》2024,33(1):58-71
In recent years,low recall rates and high dependencies on data labelling have become the biggest ob-stacle to developing deep anomaly detection(DAD)techniques.Inspired by the success of generative adversarial net-works(GANs)in detecting anomalies in computer vision and imaging,we propose an anomaly detection model called FlowGANAnomaly for detecting anomalous traffic in network intrusion detection systems(NIDS).Unlike traditional GAN-based approaches,which are composed of a flow encoder,a convolutional encoder-decoder-encoder,a flow de-coder and a convolutional encoder,the architecture of this model consists of a generator(G)and a discriminator(D).FlowGANAnomaly maps the different types of traffic feature data from separate datasets to a uniform feature space,thus can capture the normality of network traffic data more accurately in an adversarial manner to mitigate the problem of the high dependence on data labeling.Moreover,instead of simply detecting the anomalies by the output of D,we proposed a new anomaly scoring method that integrates the deviation between the output of two Gs'convo-lutional encoders with the output of D as weighted scores to improve the low recall rate of anomaly detection.We conducted several experiments comparing existing machine learning algorithms and existing deep learning methods(AutoEncoder and VAE)on four public datasets(NSL-KDD,CIC-IDS2017,CIC-DDoS2019,and UNSW-NB15).The evaluation results show that FlowGANAnomaly can significantly improve the performance of anomaly-based NIDS. 相似文献
20.
水介质的吸收和散射特性致使水下图像存在不同类型的失真,严重影响后续处理的准确性和有效性。目前有监督学习的水下图像增强方法依靠合成的水下配对图像集进行训练,然而由于合成的数据可能无法准确地模拟水下成像的基本物理机制,所以监督学习的方法很难应用于实际的应用场景。该文提出一种基于特征解耦的无监督水下图像增强方法,一方面,考虑获取同一场景下的清晰-非清晰配对数据集难度大且成本高,提出采用循环生成对抗网络将水下图像增强问题转换成风格迁移问题,实现无监督学习;另一方面,结合特征解耦方法分别提取图像的风格特征和结构特征,保证增强前后图像的结构一致性。实验结果表明,该方法可以在非配对数据训练的情况下,能够有效恢复水下图像的颜色和纹理细节。 相似文献