Sketch-then-Edit Generative Adversarial Network

Li, Wei; Xu, Linchuan; Liang, Zhixuan; Wang, Senzhang; Cao, Jiannong; Ma, Chao; Cui, Xiaohui

doi:10.1016/j.knosys.2020.106102

Cited by 14 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research on implicit inference attacks has gradually become important, and the means of reasoning will become more and more with the advancement of technology. In terms of attribute inference, in the future, attackers can obtain more powerful classifiers through adversarial machine learning, and use them for inference [92]; or collect more user information, including cross-platform data, and use the correlation between attributes to perform better attribute inference.…”

Section: Discussionmentioning

confidence: 99%

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Piao

Cui

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

With the rapid development of social networks, users pay more and more attention to the protection of personal information. However, the transmission of users' personal information through social networks will inevitably lead to privacy leakage and make users attacked. A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks. Social relationship inference and attribute inference are two basic attacks on users' privacy in social networks. This is the first systematic review of privacy inference attacks in social networks. The purpose of this retrospective study is to provide a global summary, summarizing the time trend of the topic, and show the evolution of the topic in the past 15 years. In addition, this paper discusses the trend and development of this topic and finally looks forward to future work. The contribution of our work is helpful for researchers to continue their research in this field.

show abstract

Section: Discussionmentioning

confidence: 99%

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Piao

Cui

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Networks. Generative adversarial networks (GANs) were introduced in 2014 [3] and widely applied to various application scenarios [5,8,9]. GAN is able to produce high-quality output images through the mutual game learning of (at least) two independent modules: the generative model and the discriminative model.…”

Section: Basics Of Generative Adversarialmentioning

confidence: 99%

Object‐Level Remote Sensing Image Augmentation Using U‐Net‐Based Generative Adversarial Networks

Huang

Liu

Tang

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the continuous development of deep learning in computer vision, semantic segmentation technology is constantly employed for processing remote sensing images. For instance, it is a key technology to automatically mark important objects such as ships or port land from port area remote sensing images. However, the existing supervised semantic segmentation model based on deep learning requires a large number of training samples. Otherwise, it will not be able to correctly learn the characteristics of the target objects, which results in the poor performance or even failure of semantic segmentation task. Since the target objects such as ships may move from time to time, it is nontrivial to collect enough samples to achieve satisfactory segmentation performance. And this severely hinders the performance improvement of most of existing augmentation methods. To tackle this problem, in this paper, we propose an object-level remote sensing image augmentation approach based on leveraging the U-Net-based generative adversarial networks. Specifically, our proposed approach consists two components including the semantic tag image generator and the U-Net GAN-based translator. To evaluate the effectiveness of the proposed approach, comprehensive experiments are conducted on a public dataset HRSC2016. State-of-the-art generative models, DCGAN, WGAN, and CycleGAN, are selected as baselines. According to the experimental results, our proposed approach significantly outperforms the baselines in terms of not only drawing the outlines of target objects but also capturing their meaningful details.

show abstract

“…McGraw et al [16] presented 3D segmentation based on NMF and produce meaningful results. For its application, Li et al [17] proposed the concept of sketch as an input of GANs, which is the noise transformed to the basis matrix in NMF that has the underlying features of the raw data.…”

Section: Feature Matrix Factorizationmentioning

confidence: 99%

“…Li et al [17] proposed sketch, a combination of random noise and features of the original data, produced by transforming vectors from the noise space to a basis matrix space in NMF. Following [17], we apply the pre-computed local weights to the part encodings that are factorized by the projection matrices (Fig. 2-(b)).…”

Section: Applying Local Weights To Factorized Part Encodingsmentioning

confidence: 99%

Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)

Kim,

Kim

2021

Preprint

View full text Add to dashboard Cite

We propose a 3D face generative model with local weights to increase the model's variations and expressiveness. The proposed model allows partial manipulation of the face while still learning the whole face mesh. For this purpose, we address an effective way to extract local facial features from the entire data and explore a way to manipulate them during a holistic generation. First, we factorize the latent space of the whole face to the subspace indicating different parts of the face. In addition, local weights generated by non-negative matrix factorization are applied to the factorized latent space so that the decomposed part space is semantically meaningful. We experiment with our model and observe that effective facial part manipulation is possible, and that the model's expressiveness is improved.

show abstract

Sketch-then-Edit Generative Adversarial Network

Cited by 14 publications

References 15 publications

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Object‐Level Remote Sensing Image Augmentation Using U‐Net‐Based Generative Adversarial Networks

Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)

Contact Info

Product

Resources

About