Filters








345 Hits in 6.6 sec

A Survey on Face Data Augmentation [article]

Xiang Wang and Kai Wang and Shiguo Lian
2019 arXiv   pre-print
Among all these approaches, we put the emphasis on the deep learning-based works, especially the generative adversarial networks which have been recognized as more powerful and effective tools in recent  ...  However, collecting and labeling adequate samples with high quality and balanced distributions still remains a laborious and expensive work, and various data augmentation techniques have thus been widely used  ...  Besides the color, [20] proposed an unsupervised visual attribute transfer using reconfigurable generative adversarial network to change the bang. Lv et al.  ... 
arXiv:1904.11685v1 fatcat:phcwwc7gcfablgytt6itr6xade

Image Style Transfering Based on StarGAN and Class Encoder

Xinzheng Xu, School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China; Engineering Research Center of Mine Digitalization, Ministry of Education, Xuzhou 221116, China, Jianying Chang, Shifei Ding
2022 International Journal of Software and Informatics  
StarGAN is a generative adversarial network framework used in recent years for multidomain image style transfer, which extracts features through simple down-sampling and then generates images through up-sampling  ...  In this paper, the network structure of StarGAN is improved, and a UE-StarGAN model for image style transfer is proposed by introducing U-Net and edge-promoting adversarial loss function.  ...  [15] proposed the unsupervised image style transfer model DualGAN on the basis of dual learning and L1-norm. In 2017, Isola et al.  ... 
doi:10.21655/ijsi.1673-7288.00267 fatcat:tlkggmuuzbhwhn6ywztobpsehi

Improving Shape Deformation in Unsupervised Image-to-Image Translation [chapter]

Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin
2018 Lecture Notes in Computer Science  
Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change.  ...  Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator.  ...  Improving Shape Deformation in Unsupervised Image-to-Image Translation  ... 
doi:10.1007/978-3-030-01258-8_40 fatcat:mkzrfq7ujnbrpodmbl4zvpgsbe

Deep Identity-aware Transfer of Facial Attributes [article]

Mu Li and Wangmeng Zuo and David Zhang
2018 arXiv   pre-print
This paper presents a Deep convolutional network model for Identity-Aware Transfer (DIAT) of facial attributes.  ...  For joint training of transform network and mask network, we incorporate the adversarial attribute loss, identity-aware adaptive perceptual loss, and VGG-FACE based identity loss.  ...  To this end, we adopt the generative adversarial network framework, where the generator is the attribute transfer network F (x), and the discriminator D is used to define the adversarial attribute loss  ... 
arXiv:1610.05586v2 fatcat:l4khpvjrnbgh3k6gy7csfyzfse

Geometry-Aware GAN for Face Attribute Transfer

Danlan Huang, Xiaoming Tao, Jianhua Lu, Minh N. Do
2019 IEEE Access  
In the attribute adding process, the spatial transformer network (STN) warps the source face into the desired pose and shape according to the flow, and the transfer sub-network hallucinates new components  ...  In this paper, the geometry-aware GAN, referred to as GAGAN, is proposed to address the issue of face attribute transfer with unpaired data.  ...  In contrast, the transfer of the attributes Bangs or Blond Hair requires only the edits of local facial components and only part of the face is manipulated.  ... 
doi:10.1109/access.2019.2942182 fatcat:6hrzwpid3vcv7bsetcdrmdgwvq

Improving Shape Deformation in Unsupervised Image-to-Image Translation [article]

Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin
2019 arXiv   pre-print
Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change.  ...  Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator.  ...  Recent research has extended the model to perform visual attribute transfer using neural networks [25, 13] .  ... 
arXiv:1808.04325v2 fatcat:t6et2bqiiramzmrh3g6ho4pftq

XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings [article]

Amélie Royer, Konstantinos Bousmalis, Stephan Gouws, Fred Bertsch, Inbar Mosseri, Forrester Cole, Kevin Murphy
2018 arXiv   pre-print
We introduce XGAN ("Cross-GAN"), a dual adversarial autoencoder, which captures a shared representation of the common domain semantic content in an unsupervised way, while jointly learning the domain-to-domain  ...  Style transfer usually refers to the task of applying color and texture information from a specific style image to a given content image while preserving the structure of the latter.  ...  Furthermore in this unsupervised setting we do not have access to supervision on shared domain semantic content (e.g., facial attributes such as hair color, eye color, etc.).  ... 
arXiv:1711.05139v6 fatcat:z77otptkt5chba3p4tlolmhkm4

Face Transfer with Generative Adversarial Network [article]

Runze Xu, Zhiming Zhou, Weinan Zhang, Yong Yu
2017 arXiv   pre-print
We propose an end-to-end face transfer method based on Generative Adversarial Network.  ...  Face transfer animates the facial performances of the character in the target video by a source actor. Traditional methods are typically based on face modeling.  ...  Generative Adversarial Networks Generative Adversarial Networks (GAN) (Goodfellow et al. 2014) has attained much attention in unsupervised learning during the recent 3 years.  ... 
arXiv:1710.06090v1 fatcat:tg4vftngozgj7hoqngef34cgpe

Deep Generative Adversarial Networks for Image-to-Image Translation: A Review

Aziz Alotaibi
2020 Symmetry  
Image-to-image translation with generative adversarial networks (GANs) has been intensively studied and applied to various tasks, such as multimodal image-to-image translation, super-resolution translation  ...  Figure 6 . 6 Style transfer applications with (a) inter-domain attribute transfer and (b) intra-domain attribute transfer [95] .  ...  Figure 6 . 6 Style transfer applications with (a) inter-domain attribute transfer and (b) intra-domain attribute transfer [95] .  ... 
doi:10.3390/sym12101705 fatcat:rqlwjjhrvbc6fhc4mxjjvkwk6i

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 6977-6991 PrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy.  ...  Genser, N., +, TIP 2020 9234- 9249 PrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
Lee, S., +, TMM 2021 2561-2574 Light Field Image Coding Using VVC Standard and View Synthesis Based on Dual Discriminator GAN.  ...  Kamel, A., +, TMM 2021 1330-1342 Light Field Image Coding Using VVC Standard and View Synthesis Based on Dual Discriminator GAN.  ...  ., Low-Rank Pairwise Align- ment Bilinear Network For Few-Shot Fine-Grained Image Classification; TMM 2021 1666-1680 Huang, H., see 1855 -1867 Huang, H., see Jiang, X., TMM 2021 2602-2613 Huang, J.,  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Unsupervised Eyeglasses Removal in the Wild [article]

Bingwen Hu, Zhedong Zheng, Ping Liu, Wankou Yang, Mingwu Ren
2020 arXiv   pre-print
To address the limitation, we propose a unified eyeglass removal model called Eyeglasses Removal Generative Adversarial Network (ERGAN), which could handle different types of glasses in the wild.  ...  Given two facial images with and without eyeglasses, the proposed model learns to swap the eye area in two faces.  ...  [41] presents a unified selective transfer network for arbitrary image attribute editing (STGAN), by combining difference attribute vector and selective transfer unit (STUs) in autoencoder network.  ... 
arXiv:1909.06989v4 fatcat:meigab4njrf2jm54sujzodazzi

A Survey of Deep Facial Attribute Analysis [article]

Xin Zheng, Yanqing Guo, Huaibo Huang, Yi Li, Ran He
2019 arXiv   pre-print
Second, the datasets and performance metrics commonly used in facial attribute analysis are presented.  ...  Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute  ...  A designed GAN is used to generate facial abstraction images before inputting them into a dual-path facial attribute recognition network, where the real original images are together fed into this recognition  ... 
arXiv:1812.10265v3 fatcat:tezgo2angvfefbttuoodnss6t4

Deep Visual Domain Adaptation: A Survey [article]

Mei Wang, Weihong Deng
2018 arXiv   pre-print
transferable representations by embedding domain adaptation in the pipeline of deep learning.  ...  Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow representations, deep domain adaption methods leverage deep networks to learn more  ...  Inspired by dual learning, adversarial reconstruction is adopted in deep DA with the help of dual GANs. Zhu et al.  ... 
arXiv:1802.03601v4 fatcat:d5hwwecipjfjzmh7725lmepzfe

AttGAN: Facial Attribute Editing by Only Changing What You Want [article]

Zhenliang He, Wangmeng Zuo, Meina Kan, Shiguang Shan, Xilin Chen
2018 arXiv   pre-print
Facial attribute editing aims to manipulate single or multiple attributes of a face image, i.e., to generate a new face with desired attributes while preserving other details.  ...  Besides, the adversarial learning is employed for visually realistic editing.  ...  attribute transfer network and does not involve any latent representation while AttGAN uses an encoder-decoder architecture and models the relation between the latent representation and the attributes  ... 
arXiv:1711.10678v3 fatcat:ru6d7xuxszcwnks6s7srohyzfu
« Previous Showing results 1 — 15 out of 345 results