AttGAN: Facial Attribute Editing by Only Changing What You Want
The DOI matches its Crossref record; 47 of the 52 references it cites were found in a registry or an index.
Abstract
Facial attribute editing aims to manipulate single or multiple attributes on a given face image, i.e., to generate a new face image with desired attributes while preserving other details. Recently, the generative adversarial net (GAN) and encoder-decoder architecture are usually incorporated to handle this task with promising results. Based on the encoder-decoder architecture, facial attribute editing is achieved by decoding the latent representation of a given face conditioned on the desired attributes. Some existing methods attempt to establish an attribute-independent latent representation for further attribute editing. However, such attribute-independent constraint on the latent representation is excessive because it restricts the capacity of the latent representation and may result in information loss, leading to over-smooth or distorted generation. Instead of imposing constraints on the latent representation, in this work, we propose to apply an attribute classification constraint to the generated image to just guarantee the correct change of desired attributes, i.e., to change what you want. Meanwhile, the reconstruction learning is introduced to preserve attribute-excluding details, in other words, to only change what you want. Besides, the adversarial learning is employed for visually realistic editing. These three components cooperate with each other forming an effective framework for high quality facial attribute editing, referred as AttGAN. Furthermore, the proposed method is extended for attribute style manipulation in an unsupervised manner. Experiments on two wild datasets, CelebA and LFW, show that the proposed method outperforms the state-of-the-art on realistic attribute editing with other facial details well preserved.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Other meth- ods such as lip-syncing approaches [67–69] and im- age quality metrics with support vector machine (SVM) [70] produce very high error rate when applied to detect deepfake videos from this newly produced dataset.”
From Deep learning for deepfakes creation and detection: A survey (2022) · cites this paper as [70]
Experimental — accuracy not yet measuredIn the citing paper
“AttGAN [41] is a technology for facial attribute manipulation; its attribute awareness enables precise and high-quality attribute changes, making it valuable for applications like face-swapping and age progression or regression.”
From Deepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions (2023) · cites this paper as [41]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The model is trained by Adam optimizer [41] (β1 = 0.”
MethodBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · cited 6×
“We employ AttGAN on a season dataset [37] and a painting dataset [21] and the results are shown in Fig.”
BackgroundMethodInfluentialImage-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · cited 1×
“We also employ the U-Net [38] like symmetric skip connections between the encoder and decoder, which have been shown to produce high quality results on the image translation task [39].”
MethodAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 2×
“In VAE/GAN [7], GAN [6] and VAE [5] are combined to learn a latent representation and a decoder.”
BackgroundLabaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
GAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267 · cited 1×
“For conventional face recognition [1], [2] and facial attribute prediction [3], [4] tasks, significant advances have been made along with the development of deep convolutional neural networks (CNNs) and large scale labeled datasets.”
BackgroundUnsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 2×
“DCGAN [27] uses CNN and batch normalization [28] for stable training.”
Method
Cited by
Items 701–800 of 848
Multi-OctConv: Reducing Memory Requirements in Image Generative Adversarial Networks
Francisco Tobar, M., & Torres, C. E. (2020) · International Conference of the Chilean Computer Science Society (SCCC) · doi:10.1109/sccc51225.2020.9281213
“…Image JS Image-to-Image yes MUNIT [19] 2018 Model-Feature JS Image-to-Image yes SingleGAN [20] 2018 Parameter JS Image-to-Image yes attGAN [8] 2018 Parameter EM-GP Image-to-Image yes StarGAN v2 [21] 2019 Parameter/Secondary Image JS Image-to-Image yes StyleGAN v2 [9] 2019…”
BackgroundLiu, H., Wang, Z., Sui, H., Zhu, Q., Liu, S., Chen, L., Lei, D., & Li, C. (2021) · Soft Computing · doi:10.1007/s00500-020-05475-6
Identifying Human Edited Images using a CNNPreprint
Lee, J., Lin, W., Ntalis, K., Shah, A., Tung, W., & Wulff, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03275
“Furthermore, they proposed that the image reconstruction maintains attributeexcluding details and achieved realistic to the human-eye edits, leading to the attGAN [10].”
BackgroundTRIP: Refining Image-to-Image Translation via Rival PreferencesPreprint
Yao, Y., Pan, Y., Tsang, I. W.-H., & Yao, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.13411
“We did not compare with AttGAN [6] that enforces fine-grained translation via a binary classifier, since RelGAN outperforms AttGAN, which is shown in [13].”
InfluentialFAE-GAN: facial attribute editing with multi-scale attention normalization
Zhu, J., Ouyang, P., Tao, R., Chen, X., Wang, J., & Zhan, S. (2021) · Machine Vision and Applications · doi:10.1007/s00138-021-01208-3
Self-citationLR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced NetworkPreprint
Balachandran, N., Chen, J.-C., & Chellappa, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.14690
“AttGAN [8], also feeds in an attribute vector into the bottleneck of the autoencoder within the Generative network, but its discriminative network tries to predict the attributes present in the input image rather than encoding the attributes in it.”
BackgroundMeronymNet: A Hierarchical Model for Unified and Controllable Multi-Category Object Generation
Baghel, R., Trivedi, A., Ravichandran, T., & Sarvadevabhatla, R. K. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475521
“In some cases, part attributes are used to generate these specific object types [12, 36].”
BackgroundCFMNet: Coarse-to-Fine Cascaded Feature Mapping Network for Hair Attribute Transfer
Xie, Z., Zhang, G., Yu, C., Zheng, J.-H., & Sheng, B. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-89029-2_32
Modularized Architecture of Attribute Generative Adversarial Network for Image Synthesis
Chen, K.-H., & Lin, B.-S. (2021) · IEEE International Conference on Knowledge Innovation and Invention (ICKII) · doi:10.1109/ickii51822.2021.9574660
Facial Emotion Generation using StarGAN with Differentiable Augmentation
Putri, W. C., & Basaruddin, T. (2021) · doi:10.1145/3483207.3483218
“StarGAN[10] and AttGAN [11] proposes that the task could be done with a pair of generator and discriminator.”
BackgroundSemi-Supervised Spatial Attention Method for Facial Attribute Editing
Yang, H., Han, J. H., & Moon, Y. S. (2021) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2021.10.012
“The selective facial attribute editing approaches include using residual training [2], applying a spatial attention mechanism [6], setting constraints on restoration and attributes [3,4,7], and implementing masking methods [5].”
MethodInfluentialConvergence of Batch Greenkhorn for Regularized Multimarginal Optimal TransportPreprint
Kostić, V., Salzo, S., & Pontil, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.00838
“Particularly, in machine learning, MOT is important for generative adversarial networks (GANs) [8], domain adaptation [15], Wasserstein barycenters [1], clustering [19], and Bayesian inference of joint distributions [14], among others.”
BackgroundUnsupervised Image Translation in the Wild
Ani, Y., & Amasvali, M. F. (2021) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu52992.2021.9599032
Hair Attribute Transfer via Deep Feature Fusion
Xie, Z., Su, X., Liu, S., Zhang, G., & Ma, L. (2021) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2021.18544
“3 定性评估 为了证明本文方法的有效性, 分别将其与主流 的 3 种属性转移方法 AttGAN([4]), StarGAN([5])和选择性 属性转移网络(selective transfer GAN, STGAN)([6])进 行比较.”
BackgroundInfluentialFacial Attributes Translation with Attention Consistency and Self-calibration
Xia, X., Li, N., Pang, X., Pan, X., Wu, C., & Ding, N. (2021) · International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS) · doi:10.1109/hpbdis53214.2021.9658454
Efficient Face Editing Generation Adversarial Networks Fused with Coordinate Attention
Guan, W., Wang, R., & Ma, L. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-030-89698-0_77
Sparsity Improves Unsupervised Attribute Discovery in Stylegan
Liu, S., Anirudh, R., Thiagarajan, J. J., & Bremer, P. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746150
Croft, W. B. (2020) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2020-14236
Deep Realistic Facial Editing via Label-restricted Mask Disentanglement
Song, J., Tong, F., & Chen, Z. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/5652730
RetractedImage-to-Image Translation with Semantic Decoupling Algorithm
Zhang, Q., Tian, P., & Mo, H. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9902664
Label Geometry Aware Discriminator for Conditional Generative Adversarial Networks
Sapkota, S., Khanal, B., Bhattarai, B., Khanal, B., & Kim, T. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956292
“Recent works have unified the ideas of standard adversarial loss, reconstruction loss and auxiliary classification loss to develop powerful class labeled image-to-image translation GANs with better control over target domains [4], [5], [10], [14], [15].”
BackgroundMethodInfluentialImage Attribute Modification Based on Text Guidance
Zhao, L., Li, X., Fu, C., & Chen, Z. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-8350-4_16
Guo, X. W., Rao, Q., He, K., Chen, F., Yu, B., Feng, B., Huang, J., & Yang, Q. L. (2022) · International Conference on Frontiers of Artificial Intelligence and Machine Learning (FAIML) · doi:10.1109/faiml57028.2022.00030
“StarGAN [1], AttGAN [35] and [6], [36] realize it by introducing an attribute classification loss.”
MethodPoint-of-Interests Recommendation based on User-POI Coupling Relationships
Meng, X., Zhang, M., Zhang, X., & Fang, J. (2022) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis57298.2022.10016353
User tests & techniques for the post-hoc explanation of deep learning
Delaney, E. D., Kenny, E. M., Greene, D., & Keane, M. T. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-396098-4.00019-3
Deghosting Diffusion Model for Facial Attribute Editing via Differential Activations
Gu, C., & Gromov, M. L. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-31353-0_11
One shot learning in StyleALAE: Preserving facial identity during semantic modification
Reddy, R. K., Kumar, S., Venkatesh, G. S., Gandikota, S., Khoche, S., Jayagopi, D. B., & Srinivasaraghavan, G. (2022) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3571600.3571617
“Researchers have also explored conditional GAN-based models for semantic face editing [4, 5, 15].”
BackgroundInstance-Aware Style-Swap for Disentangled Attribute-Level Image Editing
Zhou, X., Jiang, B., Yang, C., Hu, H., & Sun, M. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2385-4_31
Shunting at Arbitrary Feature Levels via Spatial Disentanglement: Toward Selective Image Translation
Wang, J., Yang, X., Tian, Y., Zhou, J., & Lv, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3282306
“With the boost of generative adversarial nets (GANs) [3], SLIT has served as the basis in a wide range of computer vision applications, such as facial attribute editing [4], [5], [6], [7], [8], instance-level translation [9], [10], [11], and so on.”
BackgroundMethodDeep learning for facial expression editing
Wu, R. (2023) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/168477
A Prior-Guided Generative Adversarial Net for Semantically Strict Ultrasound Images Augmentation
Yu, R., Sun, P., Li, X., Zhang, R., Liu, Z.-Q., & Gao, J. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-4749-2_2
Weak Segmentation-Guided GAN for Realistic Color Edition
Auriau, V., Malherbe, E., & Perrot, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43148-7_41
A Review of Face Attribute Editing Based on Deep Learning
Pang, Y., Qiang, Z., Su, S., Qingyang, C., & Lin, H. (2023) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3587716.3587737 · Cited by 2
“AttGAN proposed by He et al.[13] is similar to StarGAN, which also uses one-hot encoding for face attributes.”
BackgroundLu, W., Peng, Z., Luo, C., Xie, W., Wen, J., Lai, Z., & Shen, L. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10223136
“Current algorithms resort to the conditional signals, e.g. one-hot label representation [1] for correct synthesis of expression, and the encoder-based feature representation, i.e. skip connection [2, 8, 9] for the generator to better maintain the identity information.”
BackgroundA Layer Selection Method Based on Feature Pyramid Network for Face Attribute RecognitionPreprint
Gao, G., Liu, X., & Zhao, W. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4578824
Differential Activation-Based Facial Attribute Editing Using Semantic Segmentation
Gu, C., & Gromov, M. L. (2023) · International Russian Automation Conference (RusAutoCon) · doi:10.1109/rusautocon58002.2023.10272804
“Early approaches for facial attribute editing are based on image-level editing [9, 10], and they use adversarial loss to train generators and discriminators for each attribute from scratch.”
BackgroundFacial Attribute Editing Using Generative Adversarial Network
Upadhyay, M., Lamichhane, B. R., & Nyaupane, B. K. (2023) · Journal of Engineering and Sciences · doi:10.3126/jes2.v2i1.60394
“Our model, benefiting from the FTUs and differential attribute vectors, outperforms AttGAN [13] and ICGAN [5] significantly in terms of reconstruction quality.”
MethodInfluentialSemantic manipulation through the lens of Geometric Algebra
Evangelista, R. D. S., Pereira, A. L. D. S., de Moraes, R. F., & Fernandes, L. A. F. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103899
An Adaptive-Guidance GAN for Accurate Face Reenactment
Chai, X., Chen, J., Xu, D., & Yao, H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-50072-5_6
Multi-Scale Enhanced Dual-Stream Network for Facial Attribute Editing Localization
Huang, J., Luo, W., Huang, W., Xi, Z., Wei, K., & Huang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2585-4_11
Generating Optimized Universal Adversarial Watermark for Preventing Face Deepfake
Lv, K., Lin, W., Xu, J., Xu, W., Chen, S., & Yi, S. (2023) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom60117.2023.00216 · Cited by 1
“In AttGAN [15], an encoder-decoder architecture is proposed, considering the relationship between attributes and latent representations.”
MethodNonlinear Facial Attribute Editing Method based on Autoencoder in StyleGAN Latent Space
Kuang, Q., He, X., Yang, C., & Xie, X. (2023) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbd-ai62252.2023.00093
“Previously, there were facial attribute editing methods based on conditional autoencoder[1,2,3,4,5] These methods have made great breakthroughs in attribute manipulation ability and image detail preservation.”
BackgroundMethodLSDN Empowers the Metaverse Communication to Achieve High-Resolution Visuals with Lower Bandwidth
Guo, K., Tan, X., Chen, L., Zhu, X., Zhang, J., & Zhou, X. (2024) · ACM Transactions on Internet Technology · doi:10.1145/3672075
“SISR seeks to meticulously reconstruct the input low-resolution (LR) image, replete with coarse details, into a high-resolution (HR) image characterized by superior visual quality [18, 58].”
BackgroundFace Image Privacy Protection with Differential Private k-Anonymity
Wen, Y., Liu, B., Song, L., Cao, J., & Xie, R. (2024) · Springer eBooks · doi:10.1007/978-3-031-58222-6_4
Globally Conditioned Conditional FLOW (GCC-FLOW) for Sea Clutter Data Augmentation
Lee, S., & Chung, W. (2024) · Applied Sciences · doi:10.3390/app14156538
Semantic facial features and expression manipulation using multi-level IC-DGAN framework
Abbas, F., & Taeihagh, A. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650839 · Cited by 1
“The comparative analysis of our IC-DGAN with benchmark method against Ex-prGAN [18], InterFGAN [19], CycleGAN [36], StyleGANEX [20], Att-GAN [37], and Vec-GAN [38]) are summarized in Table 2.”
MethodExplicit Facial Attribute Disentanglement for Hierarchical Relationships Detection
Sun, P., Yu, H. Q., Xie, J., Leng, J., & Wang, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-7007-6_16
Text-Conditional Attribute Alignment Across Latent Spaces for 3D Controllable Face Image Synthesis
Xu, F., Li, R., Wu, S., Xu, Y., & Wong, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00876 · Cited by 1
“Except for image translation, the generator can be conditioned on some predefined factors [16, 43] for controllable editing.”
Park, C., Kim, S., Lee, D., Lee, S., Ashok, K., Park, C., & Kim, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72104-5_15
Comparison of GANs for Speech to Face Generation Using a Custom Indian Face Dataset
Raghavan, A., Harkude, A., Brahmadevara, U., Ashritha, D., & Vinodha, K. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-4228-8_34
Dual-Task Cascaded for Proactive Deepfake Detection Using QPCET Watermarking
Wang, C., Shi, C., Liu, Y., Xia, Z., Li, J., Xian, Y., & Ma, B. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8490-5_10
Güncel Deepfake Video Algılama Yöntemleri Üzerine Bir Literatür İncelemesi
Aydın, S., & Özen, Z. (2024) · Bilgisayar bilimleri ve mühendisliği dergisi. · doi:10.54525/bbmd.1460699
Self-Attention Facial Attribute Editing
Zhang, H., & Liu, B. (2024) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3697355.3697371
“[ 10] further enhances the attribute classifier, ensuring that the generated editing results possess both the correct target attributes and retain irrelevant attributes as inputs to the discriminator, thereby training generators with more accurate semantic directions.”
Typeface Generation through Style Descriptions With Generative Models
Wang, P., Zhang, X., Zhou, Z., Childs, P., Lee, K.-P., Kleinsmann, M. S., & Wang, S. J. (2024) · ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI) · doi:10.1145/3703619.3706043
Robust style injection for person image synthesis
Huang, Y., Qian, J., Zhu, S., Li, J., & Yang, J. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12361
Universal Face Manipulation Proactive Defense by Frequency-Driven Imperceptible Adversarial Attack
Wen, J., Wang, J., Sun, Y., & Massimo Tistarelli, A. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1071-6_18
Face2Makeup: Generating Facial Makeup Images via Diffusion Model
Huang, Z., Chen, X., Wei, H., Su, Z., Liu, Y., & Dong, Z. (2024) · IEEE International Conference on Data Science and Computer Application (ICDSCA) · doi:10.1109/icdsca63855.2024.10859454
Self-citationExploration of Deep Generative Models for Addressing Data Imbalance in Computer Vision
Priyadharshini, A., & Karpagavalli, S. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-97-8096-9_39
Cross-Modal Attention Fusion Based Generative Adversarial Network for Text-to-Image Synthesis
Chen, X., & Luo, X. (2024) · Springer eBooks · doi:10.1007/978-3-031-80965-1_14
Self-citationImproving Artistic Design With KFDeformNet: Single-Frame Three-Dimensional Cartoon Face Recovery
Sun, T., Wang, X., & Qi, Y. (2025) · IEEE Access · doi:10.1109/access.2025.3551397 · Cited by 1
“When employing autoencoder network structures for 3D face recovery, many algorithms use a single encoder to encode different facial attributes [44], [45], [46].”
Advancing Image Forensic: Detecting Facial Manipulations via Meso_KNN
Issa, H., & Zarnahji, B. (2025) · Tehnički glasnik · doi:10.31803/tg-20231220161257 · Cited by 1
SKTNet: a semantically guided attribute disentanglement network for fashion sketch editing
Zhang, P., Wei, M., Sun, K., Zhang, J., Fei, B., & Zhan, J. (2025) · Textile Research Journal · doi:10.1177/00405175241305792
“Fashion AttGAN 20 improves upon AttGAN 21 by adding extra optimization objectives, thus making AttGAN’s structure more suitable for the fashion domain.”
Zhu, H., Liu, B., Wei, X., Han, G., Zhang, W., Ma, Y., & Darwesh, A. M. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3571812
“Tables III and IV show that the siamese framework out-performs ATTGAN [4] and STGAN [5] across all metrics.”
TapFace: A task-oriented facial privacy protection framework
Liu, Z., Zhou, Y., Xiong, P., & Wang, Q. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104497
Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN
Han, F., Hao, G., Guerrero, R., & Pavlović, V. (2021) · British Machine Vision Conference (BMVC) · doi:10.5244/c.35.402
Гу, Ч., & Gromov, M. L. (2025) · Modelirovanie, optimizaciâ i informacionnye tehnologii. · doi:10.26102/2310-6018/2025.49.2.046
Detecting Near-Duplicate Face Images
Banerjee, S., & Ross, A. A. (2025) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2025.3548541
“1 Photo-editing filters and generative models such as generative adversarial networks (GANs) and diffusion models can be used to alter the appearance of any individual by modifying facial and demographic attributes such as age and hairstyle [4], [5].”
A Comprehensive Review of AI in Fashion
Suman, S., Upadhya, P., Mohammed, M., Shriya, M. S., & Katharguppe, S. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-92625-9_7
Robust and Unstigmatized Imperceptible Perturbations for Rendering Face Manipulation Ineffective
Zhang, Y., Lin, W., Tian, Z., Min, G., Xu, J., & Xu, Y. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3592565 · Cited by 4
“In the attribute editing experiments, we employ four representative models: StarGAN [3], AttGAN [4], HiSD [5], and Atten-tionGAN [6].”
Face Deepfake Detection Based on Up-Sampling Feature Extraction and CNN
Tang, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94962-3_12
Latent Multi-Attribute Transformer for Face Editing in Images
Carasquilla, A., Ruiz, M., Radeva, P. I., & Aghaei, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-99965-9_17
A Comprehensive Review of Deepfake Detection Technologies
Bharti, Gaur, R., & Kalpana (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5535-9_31
Contrastive Steering Vectors for Autoencoder Explainability
Mora, J. G. G., Ponce-Espinosa, H., & Martínez-Villaseñor, L. (2025) · Electronics · doi:10.3390/electronics14183586
FaceDisentGAN: Disentangled facial editing with targeted semantic alignment
Xu, M., Hamandawana, P., Ma, X., Chen, Z., Jin, R., & Chung, T. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131706
Seeing is No Longer Believing: How Deepfakes May Shape the Future of Identity Credibility in Media
Frick, R. A., Bunzel, N., & Graner, L. (2025) · ACM Workshop on Deepfake, Deception, and Disinformation Security (3D-Sec) · doi:10.1145/3733813.3764371 · Cited by 1
“Image Editing: GANs can edit facial attributes (e.g., age, hair color) by mapping images to latent space and modifying its vectors [24, 32], though this may blur details or unintentionally change multiple traits.”
Wei, H., Xu, H., Zhu, B., Geng, Y., Liu, A., Yin, W., & Liu, J. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11208933
“On the Glomeruli Segmentation Dataset [4], we utilize the same network (Mask R-CNN [26]) to detect and segment glomeruli in both H&E-stained images and their virtually converted stained counterparts generated by our model.”
GAN semantics for personalized facial beauty synthesis and enhancement
Lebedeva, I., Ying, F., Guo, Y., & Li, T. (2025) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2025.104640
NouMenn: Accurate Reconstructive Privacy Protection for Facial Soft Attributes via Style Code
Fang, Z., Jin, B., & Zhang, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228280
“A scheme focused on simultaneously deceiving both classifiers and human observers is called Face Attribute Manipulation, with some schemes balancing modification intensity and identity utility preservation [28], [29].”
Wang, Y., Liang, Y., Ma, B., Zhang, P., & Wang, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4381-6_32 · Cited by 1
RetractedDisruptive Attacks on Face Swapping via Low-Frequency Perceptual Perturbations
Huang, M., Shu, M., Zhou, S., & Liu, Z. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228245
Dynamic dual consistency distillation for imbalanced facial attribute editing
Zhang, F., Huang, X., Wan, H., Xu, J., Li, M., & Wei, X. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114932
Towards Interpretable Face Morphing via Unsupervised Learning of Layer‐Wise and Local Features
Yu, C., Chen, C., & Wang, W. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70088
Shen, S., Zhang, Y., Ye, D., Shi, X., Tang, L., Duan, H., Shang, Y., & Tian, Z. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3639912
“2, we built the ErasableMask framework using a conditional GAN architecture [40].”
Bukhari, M., & Maqsood, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130720
MFI-LPO: Feature competition-driven perturbation for evading facial manipulation systems
Tao, Y., Xie, X., Shi, Y., Shi, L., Wei, L., Gao, Y., & Wu, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132221
Fake Money, Real Threat: Fooling Wavelet-Based Banknote Authentication with AdvGAN
Knaup, J., Holst, C., & Lohweg, V. (2025) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz67716.2025.11281820
“For example, H E et al. proposed AttGAN , a cGAN framework for facial attribute editing that modifies specific features (e. g. age or hairstyle) while preserving other aspects of the image [4].”
Fine-Grained Meta-Learning with Semantic Augmentation for SAR Change Detection
Wang, R., Liu, C., Sun, L., Wang, L., Ly, V. D., & Jiao, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228275
“For example, GAN-based methods [17–19] have been employed to generate semantically meaningful synthetic samples, complementing traditional augmentation techniques.”
Balancing Ethical Implications of Using AI and Deepfake Technology for Academic Purposes
Sudha, P. M., Seshadri, U., Acharya, R., Bhargava, A., Banu, M. S., & Sulthana, M. R. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-3770-8.ch001
Implementing Cybersecurity Policies to Minimize the Impacts of Deepfakes on Universities
Manikandan, S., Minu, M. S., Ramesh, S. S. S., Sivasankari, K., Saranya, S., & Singh, S. K. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-3770-8.ch016
Optimization Accuracy of Deep Fake Face Detection Using DenseNet Structure
Oderiya, P., Tiwari, D., & Gupta, S. (2026) · Lecture notes in networks and systems · doi:10.1007/978-981-95-2872-1_36
Multi-scale Spatial Frequency Interaction Variance Perception Model for Deepfake Face Detection
Wang, Y., Liu, S., Chen, X., Kim, S. T., & Li, X. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104719 · Cited by 1
Self-citationResearch on Adversarial Sample Generation Algorithm Based on Face Recognition
王, 宇. (2026) · Computer Science and Application · doi:10.12677/csa.2026.161027
Adaptive Multi-Feature Hierarchical Framework for Generative Model Attribution
Wang, R., Li, L., Si, X., Yuan, K., & Wang, Z. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00391
“The first category covers nine generative adversarial network (GAN) architectures: AttGAN [16], BigGAN [17], CycleGAN [18], GDWCT [19], ProGAN [20], StarGAN [21], StarGAN-v2 [22], StyleGAN [14], and StyleGAN2 [3], each contributing 2,500 samples for a total of 22,500.”
Active Defense for Deepfakes Using Watermark-Guided Original Face Recovery
Guo, Y., Liu, Z., Li, Y., & Feng, B. (2026) · Electronics · doi:10.3390/electronics15030625
Null Text-Guided Interactive Image Editing for Diffusion Models
Wang, J., & Luo, H. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00200
“GANs have been widely employed in image style transfer [15, 16], image-to-image translation [7, 44], and semantic manipulation [11, 26, 29].”
Beyond Global Perturbations: Focused Adversarial Attacks for Face Deepfake
Cao, Z., Wang, Z., Wang, R., Ai, H., & Wu, G. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3669723 · Cited by 1
“StarGAN [28] incorporates domain labels as conditional inputs, allowing attribute control through vector splicing and enabling the addition of features such as Black Hair, Blond Hair, Brown Hair, Male, and Young.”
Certified Attribute Privacy in Gan Latent Space
Arbas, J., Ghaffaripour, S., & Miri, A. (2025) · IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA) · doi:10.1109/tps-isa67132.2025.00084
“AttGAN [27] preserves unrelated features during edits, while StyleFlow [28] enables invertible, attribute-conditional navigation in latent space, moving beyond simplistic linear traversals.”
Pervin, M. T., Tavakkoli, A., George Bebis, A., & Jiang, F. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6333532
Metadata
- Authors
- He, Z., Zuo, W., Kan, M., Shan, S., & Chen, X.
- Affiliations
- Chinese Academy of Sciences (CN)
- Harbin Institute of Technology (CN)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2019-11
- Volume
- 28
- Issue
- 11
- Pages
- 5464-5478
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W2963626105
- Cited by
- 833
- References
- 52
- Citations by year
- 2026: 57 · 2025: 110 · 2024: 113 · 2023: 134 · 2022: 115 · 2021: 158 · 2020: 112 · 2019: 32
- FWCI
- 46.59
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Key R&D Program of China (2017YFA0700800)
- National Natural Science Foundation of China (61671182, 61772496, 61732004)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- facial attribute editing, generative adversarial networks, encoder-decoder architecture, latent representations, face synthesis, CelebA, Labeled Faces in the Wild
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.