【摘 要】
:
With the development of face image syn-thesis and generation technology based on generative ad-versarial networks(GANs),it has become a research hot-spot to determine whether a given face image is natural or generated.However,the generalization capability
【机 构】
:
Engineering Research Center of Digital Forensics,Ministry of Education,Nanjing University of Informa
论文部分内容阅读
With the development of face image syn-thesis and generation technology based on generative ad-versarial networks(GANs),it has become a research hot-spot to determine whether a given face image is natural or generated.However,the generalization capability of the existing algorithms is still to be improved.Therefore,this paper proposes a general algorithm.To do so,firstly,the learning on important local areas,containing many face key-points,is strengthened by combining the global and local features.Secondly,metric learning based on the ArcFace loss is applied to extract common and discrimin-ative features.Finally,the extracted features are fed into the classification module to detect GAN-generated faces.The experiments are conducted on two publicly available natural datasets(CelebA and FFHQ)and seven GAN-generated datasets.Experimental results demonstrate that the proposed algorithm achieves a better generalization performance with an average detection accuracy over 0.99 than the state-of-the-art algorithms.Moreover,the pro-posed algorithm is robust against additional attacks,such as Gaussian blur,and Gaussian noise addition.
其他文献
GIFT is a lightweight block cipher with an substitution-permutation-network(SPN)structure proposed in CHES 2017.It has two different versions whose block sizes are 64 and 128 respectively.In RSA 2019,Zhu et al.found some differential characteristics of GI
第五代移动通信技术(5G)已正式投入商用,卫星网络与地面移动通信系统的融合是其中一个重要研究方向.针对5G体制在低轨(Low Earth Orbiting,LEO)卫星场景中应用的适应性问题,总结了不同研究机构、标准化组织以及学术界的研究进展,分析了由于卫星互联网特点带来的5G空口影响与挑战,给出了低轨卫星互联网5G空口的时频同步、随机接入以及小区切换现有解决方案.相关内容可为低轨卫星互联网与5G的融合研究提供参考.
In this paper,a novel maximum corren-tropy high-order extended Kalman filter(H-MCEKF)is proposed for a class of nonlinear non-Gaussian systems presented by polynomial form.All high-order polynomial terms in the state model are defined as implicit variable
The conventional convolutional neural network performs not well enough in the ground objects classification because of its insufficient ability in maintain-ing sensitive spectral information and characterizing the covariance of spatial structure,resulting
In this paper,a hybrid deep learning network-based model is proposed and implemented for maneuver decision-making in an air combat environment.The model consists of stacked sparse auto-encoder net-work for dimensionality reduction of high-dimensional,dyna
Unsupervised person re-identification(Re-ID)aims to improve the model\'s scalability and ob-tain better Re-ID results in the unlabeled data domain.In this paper,we propose an unsupervised person Re-ID method based on multi-granularity feature representa
A new classification model,the fuzzy hy-brid twin support vector machine(TWSVM),namely FHTWSVM,is proposed by combining the fuzzy TWS-VM and the hypersphere support vector machine(SVM).The hypersphere SVM is utilized for generating the hy-perspheres for t
2月16日,据世界经济论坛网站发布的WEF智能工业指数认证白皮书《制造业转型洞察报告》显示,海尔洗衣机旗下中德滚筒互联工厂和海尔合肥洗衣机互联工厂入选该报告,成为全球洗衣机行业唯一入选的优秀案例代表,再次证明了海尔洗衣机的智能制造实力.
Speech emotion recognition(SER)is the use of speech signals to estimate the state of emotion.At present,machine learning is one of the main research methods of SER,the test and training dataS of tradition-al machine learning all have the same distribution
This paper reports a successive approx-imation register(SAR)analog-to-digital converters(ADCs)with the 2nd-order and optimized noise shaping(NS)scheme.Based on the feed-forward structure,both noise transfer function(NTF)zero and pole optimization have bee