The DOI matches its Crossref record; 47 of the 52 references it cites were found in a registry or an index.
AttGAN: Facial Attribute Editing by Only Changing What You Want
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
Deepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3130191 · Cited by 1,231
“Other related works can be found in [246], [247].”
BackgroundArtificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793
“2018b), and to change facial attributes, such as the presence of a beard, skin condition, hair style and color (He et al. 2019).”
BackgroundMasood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023) · Applied Intelligence · doi:10.1007/s10489-022-03766-z · Cited by 543
“In AttGAN [108], an encoder-decoder architecture was proposed that considers the relationship between attributes and latent representation.”
BackgroundMethodInfluentialExplainable machine learning in materials science
Zhong, X., Gallagher, B., Liu, S., Kailkhura, B., Hiszpanski, A., & Han, T. Y.-J. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00884-7 · Cited by 501
Multimodal intelligence: Representation learning, information fusion, and applications
Zhang, C., Yang, Z., He, X., & Deng, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2987728 · Cited by 511
“[215] uses the same idea for face editing, such as to remove the beard or change the hair color.”
MethodCounterfactual explanations and how to find them: literature review and benchmarking
Guidotti, R. (2024) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00831-6 · Cited by 471
Deep learning for deepfakes creation and detection: A survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103525 · Cited by 464
Deep Learning for Deepfakes Creation and Detection: A Survey
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh-The, T., Nahavandi, S., Nguyen, T. T., Pham, Q.-V., & Nguyen, C. M. (2019) · arXiv · doi:10.48550/arxiv.1909.11573 · Cited by 464
Image-to-Image Translation: Methods and Applications
Pang, Y., Lin, J., Qin, T., & Chen, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3109419 · Cited by 378
A Survey on Generative Adversarial Networks: Variants, Applications, and Training
Jabbar, A., Li, X., & Omar, B. (2022) · ACM Computing Surveys · doi:10.1145/3463475 · Cited by 360
“to Editor, a user can make any adjustment on the given photo with the help of rough brush striking. Another high eminence facial characteristic editing framework referred to as Attribute GAN (AttGAN) [73] uses encoder-decoder structural design and takes the facial feature information as a component of the latent vecto…”
MethodDeepFake Detection by Analyzing Convolutional Traces
Guarnera, L., Giudice, O., & Battiato, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00341 · Cited by 374
“In this paper, the five most famous and effective architectures in state-of-the-art for face Deepfakes were taken into account: STARGAN [6], STYLEGAN [19], STYLE-GAN2 [20], ATTGAN [15] and GDWCT [5].”
BackgroundMethodInfluentialDiffusion Autoencoders: Toward a Meaningful and Decodable Representation
Preechakul, K., Chatthee, N., Wizadwongsa, S., & Suwajanakorn, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01036 · Cited by 338
“Besides producing impressive image samples, GANs [15] have been shown to learn meaningful latent spaces [27] with extensive studies on multiple derived spaces [24, 57] and various knobs and controls for conditional human face generation [21, 37, 55].”
BackgroundAttention, please! A survey of neural attention models in deep learning
de Santana Correia, A., & Colombini, E. L. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10148-x · Cited by 298
Generative Adversarial Networks for face generation: A survey
Kammoun, A., Slama, R., Tabia, H., Ouni, T., & Abid, M. (2022) · ACM Computing Surveys · doi:10.1145/1122445.1122456 · Cited by 311
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
Chen, D., Yu, N., Zhang, Y., & Fritz, M. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3417238 · Cited by 311
“r Attacker’s reference generator, described in Section 5.6 θv Victim model’s parameter θr Attacker’s reference model’s parameter Table 2: Notations. image processing [22] and facial attribute editing [27, 37]. This is another novel setting and not considered in previous works [25, 29]. It corresponds to the third last…”
BackgroundInfluentialDeepFake Detection for Human Face Images and Videos: A Survey
Malik, A., Kuribayashi, M., Abdullahi, S. M., & Khan, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3151186 · Cited by 297
“The available techniques, such as image-level manipulation through popular GAN architectures [32], [33] and some popular video-based manipulation techniques, such as Face2Face [34] and neural textures [35], replace one person’s facial expression in a video with another person’s facial expression.”
MethodDeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · arXiv · doi:10.48550/arxiv.2006.07634 · Cited by 280
“e adversarial network (GAN) [22] for the nearrealistic face synthesis. Moreover, some methods can even alter face attributes, e.g., changing or removing the color of the hair, adding glasses or scars [8, 21, 30, 63], and modifying persons’ facial expression [41]. Overall, GANs have shown great potential in this area a…”
MethodA survey on generative adversarial networks for imbalance problems in computer vision tasks
Sampath, V., Maurtua, I., Aguilar Martín, J. J., & Gutierrez, A. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00414-0 · Cited by 259
Editing in Style: Uncovering the Local Semantics of GANs
Collins, E., Bala, R., Price, B., & Susstrunk, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00581 · Cited by 268
Controllable Person Image Synthesis With Attribute-Decomposed GAN
Men, Y., Mao, Y., Jiang, Y., Ma, W.-Y., & Lian, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00513 · Cited by 258
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
“Other related works can be found in [246], [247].”
BackgroundDash, A., Ye, J., & Wang, G. (2024) · IEEE Access · doi:10.1109/access.2023.3346273 · Cited by 211
“Yuan et al. [170] presented Design-AttGAN, a new version of attribute GAN (AttGAN) [172] to edit garment images automatically based on certain user-defined attributes.”
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
Qi, H., Guo, Q., Juefei-Xu, F., Xie, X., Ma, L., Feng, W., Liu, Y., & Zhao, J. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413707 · Cited by 220
“e adversarial network (GAN) [22] for the nearrealistic face synthesis. Moreover, some methods can even alter face attributes, e.g., changing or removing the color of the hair, adding glasses or scars [8, 21, 30, 63], and modifying persons’ facial expression [41]. Overall, GANs have shown great potential in this area a…”
MethodTan, C., Zhao, Y., Wei, S., Gu, G., Liu, P., & Wei, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i5.28310 · Cited by 215
“AttGAN BEGAN CramerGAN InfoMaxGAN MMDGAN RelGAN S3GAN SNGAN STGAN Mean Acc.”
A survey of face recognition techniques under occlusion
Zeng, D., Veldhuis, R., & Spreeuwers, L. (2021) · IET Biometrics · doi:10.1049/bme2.12029 · Cited by 196
A State-of-the-Art Review on Image Synthesis With Generative Adversarial Networks
Wang, L., Chen, W., Yang, W., Bi, F., & Yu, F. R. (2020) · IEEE Access · doi:10.1109/access.2020.2982224 · Cited by 197
Ten years of generative adversarial nets (GANs): a survey of the state-of-the-art
Chakraborty, T., Reddy K S, U., Naik, S. M., Panja, M., & Manvitha, B. (2024) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/ad1f77 · Cited by 174
“It was introduced by He et al in 2019 in their work ‘AttGAN: Facial Attribute Editing by Only Changing What You Want’ [124].”
BackgroundMethodCountering Malicious DeepFakes: Survey, Battleground, and Horizon
Juefei-Xu, F., Wang, R., Huang, Y., Guo, Q., Ma, L., & Liu, Y. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01606-8 · Cited by 191
“StarGAN (Choi et al., 2018) AttGAN (He et al., 2019b) Apply an attribute classification constraint to the generated image.”
BackgroundMethodInfluentialDeepfake generation and detection: Case study and challenges
Patel, Y., Tanwar, S., Gupta, R., Bhattacharya, P., Davidson, I. E., Nyameko, R., Aluvala, S., & Vimal, V. (2023) · IEEE Access · doi:10.1109/access.2023.3342107 · Cited by 186
“AttGAN [56] also follows a similar kind of architecture.”
BackgroundRegularizing Deep Networks with Semantic Data Augmentation
Wang, Y., Huang, G., Song, S., Pan, X., Xia, Y., & Wu, C. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3052951 · Cited by 163
Image-to-image Translation via Hierarchical Style Disentanglement
Li, X., Zhang, S., Hu, J., Cao, L., Hong, X., Mao, X., Huang, F., Wu, Y., & Ji, R. (2021) · 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/cvpr46437.2021.00853 · Cited by 203
“Our framework focuses on the broad concept of image-to-image translation to jointly solve multi-label [5, 11, 20, 38] and multistyle [15, 18, 1, 48] issues, and overcomes the disadvantages of previous joint frameworks [34, 36, 42, 19, 6, 39, 46, 40, 10].”
BackgroundMethodOnly a matter of style: age transformation using a style-based regression model
Alaluf, Y., Patashnik, O., & Cohen‐Or, D. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459805 · Cited by 168
“More recent works [He et al. 2018; Lample et al. 2018; Li et al. 2019; Or-El et al. 2020; Yao et al. 2020] take a data-driven approach for modeling face aging by using deep neural networks for image synthesis.”
MethodFighting Deepfake by Exposing the Convolutional Traces on Images
Guarnera, L., Giudice, O., & Battiato, S. (2020) · IEEE Access · doi:10.1109/access.2020.3023037 · Cited by 149
A comprehensive overview of Deepfake: generation, detection, datasets, and opportunities
Seow, J. W., Lim, M. K., Phan, R. C. W., & Liu, J. K. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.09.135 · Cited by 149
Implicit Semantic Data Augmentation for Deep NetworksPreprint
Wang, Y., Pan, X., Song, S., Zhang, H., Wu, C., & Huang, G. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.12220 · Cited by 242
“Variational Autoencoder(VAE) and Generative Adversarial Network(GAN) based methods [24, 25, 26] establish a latent representation corresponding to the abstractions of images, which can be manipulated to edit the semantics of images.”
MethodPrivacyNet: Semi-Adversarial Networks for Multi-Attribute Face Privacy
Mirjalili, V., Raschka, S., & Ross, A. A. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3024026 · Cited by 166
“With the development of Generative Adversarial Networks (GANs) [72]–[74], different GAN-based models for editing facial attributes have been proposed in the literature [75]–[79].”
BackgroundTowards Flexible Blind JPEG Artifacts Removal
Jiang, J., Zhang, K., & Timofte, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00495 · Cited by 207
“text-to-image generation [26, 35, 43] and facial attribute editing [9, 21, 27].”
BackgroundA survey on face data augmentation for the training of deep neural networks
Wang, X., Wang, K., & Lian, S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04748-3 · Cited by 141
RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
Lin, Y., Wu, P.-W., Chang, C.-H., Chang, E. Y., & Liao, S.-W. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00601 · Cited by 179
“Despite the impressive results of recent multi-domain methods [4, 7], they have two limitations.”
BackgroundMethodInfluentialGAN-Control: Explicitly Controllable GANs
Shoshan, A., Bhonker, N., Kviatkovsky, I., & Medioni, G. G. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01382 · Cited by 189
“Image editing: Rather than generating images de novo, these methods receive an image as input and manipulate its attributes either by using image-to-image translation techniques [58, 52, 39, 37, 11, 12, 25], by incorporating pretrained models to supervise GAN’s training [46, 8, 23, 54], or by projecting the image to t…”
MethodGenerative Adversarial Networks for Face Generation: A Survey
Kammoun, A., Slama, R., Tabia, H., Ouni, T., & Abid, M. (2022) · ACM Computing Surveys · doi:10.1145/3527850 · Cited by 170
“He et al. [53] consider the relation between attributes and the latent representation and propose a facial attribute editing method called Att-GAN , which incorporates attribute classification constraint, reconstruction learning, and adversarial learning for high-quality facial attribute editing.”
BackgroundMethodCMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes
Huang, H., Wang, Y., Chen, Z., Zhang, Y., Li, Y., Tang, Z., Chu, W., Chen, J., Lin, W., & Ma, K. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19982 · Cited by 167
On generating trustworthy counterfactual explanations
Del Ser, J., Barredo-Arrieta, A., Díaz-Rodríguez, N., Herrera, F., Saranti, A., & Holzinger, A. (2024) · Information Sciences · doi:10.1016/j.ins.2023.119898 · Cited by 122
Deep Learning for Deepfakes Creation and Detection: A SurveyPreprint
Nguyen, T. T., Nguyen, M. C., Nguyen, D. T., Nguyen, D. T., & Nahavandi, S. (2020) · arXiv (Cornell University) · doi:10.6084/m9.figshare.12731039.v1 · Cited by 124
Detect and locate: Exposing face manipulation by semantic-and noise-level telltales
Kong, C., Chen, B., Li, H., Wang, S., Rocha, A., & Kwong, S. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3169921 · Cited by 120
“Herein, we employ the popular StyleGAN [57] and PGGAN [58] to produce 40000 entirely synthetic faces and use StarGAN [59] and AttGAN [60] to generate 40000 attribute-manipulated faces (two attribute manipulations are considered in this paper: glasses and hairs).”
MethodFighting Deepfakes by Detecting GAN DCT Anomalies
Giudice, O., Guarnera, L., & Battiato, S. (2021) · Journal of Imaging · doi:10.3390/jimaging7080128 · Cited by 118
“Different Deepfake images were generated considering StarGAN, GDWCT, AttGAN, StyleGAN and StyleGAN2 architectures.”
MethodInfluentialEditGAN: High-Precision Semantic Image EditingPreprint
Ling, H., Kreis, K., Li, D., Kim, S. W., Torralba, A. B., & Fidler, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.03186 · Cited by 271
“(iii) Furthermore, auxiliary attribute classifiers have been used for image manipulation [23, 15], thereby still relying on annotated data and usually only providing high-level control.”
BackgroundDeepfake Attacks: Generation, Detection, Datasets, Challenges, and Research Directions
Naitali, A., Ridouani, M., Salahdine, F., & Kaabouch, N. (2023) · Computers · doi:10.3390/computers12100216 · Cited by 117
“The five currently accessible architectures are GDWCT [67], StarGAN [68], AttGAN [41], StyleGAN [42], and StyleGAN2 [69].”
MethodLearning disentangled representations in the imaging domain
Liu, X., Sanchez, P., Thermos, S., O’Neil, A. Q., & Tsaftaris, S. A. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102516 · Cited by 167
Deepfakes generation and detection: a short survey
Akhtar, Z. (2023) · Journal of Imaging · doi:10.3390/jimaging9010018 · Cited by 106
“, FaceApp [6], ZAO [7], Face Swap Live [8], Deepfake web [9], AgingBooth [10], PotraitPro Studio [11], Reface [12], Audacity [13], Soundforge [14], Adobe Photoshop [15]), and Deep Neural network (DNN) source codes [16,17] have enabled even non-experts and non-technical people to”
BackgroundGenerative Counterfactual Introspection for Explainable Deep Learning
Liu, S., Kailkhura, B., Loveland, D., & Han, T. Y.-J. (2019) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip45357.2019.8969491 · Cited by 134
“The classifier [11] is trained on CelebA dataset and achieves average accuracy of 90.”
MethodInfluentialFakeLocator: Robust Localization of GAN-Based Face Manipulations
Huang, Y., Juefei-Xu, F., Guo, Q., Liu, Y., & Pu, G. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3141262 · Cited by 102
“We select STGAN, StyleGAN, AttGAN, StarGAN, IcGAN, PGGAN, StyleGAN2 and all their properties.”
MethodInfluentialAdversarial Attacks Against Face Recognition: A Comprehensive Study
Vakhshiteh, F., Nickabadi, A., & Ramachandra, R. (2021) · IEEE Access · doi:10.1109/access.2021.3092646 · Cited by 126
High-Fidelity and Arbitrary Face Editing
Gao, Y., Wei, F., Bao, J., Gu, S., Chen, D., Wen, F., & Lian, Z. (2021) · 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/cvpr46437.2021.01585 · Cited by 97
“With the rapid development of Generative Adversarial Networks (GANs) [11], many recent works on face editing [19, 6, 15, 24, 33, 8] leverage the advanced conditional GANs and achieve remarkable progress.”
BackgroundGenerative adversarial networks review in earthquake-related engineering fields
Marano, G. C., Rosso, M. M., Aloisio, A., & Cirrincione, G. (2023) · Bulletin of Earthquake Engineering · doi:10.1007/s10518-023-01645-7 · Cited by 116
A Latent Transformer for Disentangled Face Editing in Images and Videos
Yao, X., Newson, A., Gousseau, Y., & Pierre Hellier, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01353 · Cited by 99
“AttGAN [15] and STGAN [25] enhanced the flexible translation of attributes to improve the image quality by relaxing the strict constraints on the target attributes.”
BackgroundSemantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers
Joshi, A., Mukherjee, A., Sarkar, S., & Hegde, C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00487 · Cited by 134
“[20] argue that such an attribute invariant constraint is too constrictive and replace it an attribute classification constraint and a reconstruction loss instead to alter only the desired attributes preserving attribute-excluding features.”
BackgroundMethodInfluentialFakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
Wang, R., Juefei-Xu, F., Luo, M., Liu, Y., & Wang, L. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475518 · Cited by 135
Deep CNN and Deep GAN in Computational Visual Perception‐Driven Image Analysis
Abirami, R. N., Vincent, P. M. D. R., Srinivasan, K., Tariq, U., & Chang, C. (2021) · Complexity · doi:10.1155/2021/5541134 · Cited by 102
“GAN-based methods have been proposed for facial attribute editing, which changes only the desired attributes and preserves the other identities of the facial images, retaining the facial image’s identity [130].”
SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains
Ko, K., Yeom, T., & Lee, M. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.02.042 · Cited by 95
Restricted Black-Box Adversarial Attack Against DeepFake Face Swapping
Dong, J., Wang, Y., Lai, J., & Xie, X. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3266702 · Cited by 124
“Exemplary results for AttGAN [38] with the input of legitimate face images and adversarial face images.”
BackgroundResultInfluentialSINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field
Bao, C. G., Zhang, Y., Yang, B., Fan, T., Yang, Z., Bao, H., Zhang, G., & Cui, Z. (2023) · 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/cvpr52729.2023.02004 · Cited by 83
Deep models of superficial face judgments
Peterson, J. C., Uddenberg, S., Griffiths, T. L., Todorov, A., & Suchow, J. W. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2115228119 · Cited by 82
“, glasses), gaze, and facial expression, are commonly studied in computer vision, where they are referred to as “attributes” (25) or “soft biometrics” (26).”
BackgroundConditional GAN with 3D discriminator for MRI generation of Alzheimer’s disease progression
Jung, E., Luna, M., & Park, S. H. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109061 · Cited by 87
Sketch2Photo: Synthesizing photo-realistic images from sketches via global contexts
Liu, H., Yao, X., & Chen, F. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105608 · Cited by 89
Repurposing GANs for One-shot Semantic Part Segmentation
Tritrong, N., Rewatbowornwong, P., & Suwajanakorn, S. (2021) · 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/cvpr46437.2021.00445 · Cited by 121
Li, J., Xu, Z., Fu, L., Zhou, X., & Yu, H. (2021) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2020.102946 · Cited by 80
Sun, Z., Zhang, H., Bai, J., Liu, M., & Hu, Z. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109157 · Cited by 82
The face deepfake detection challenge
Guarnera, L., Giudice, O., Guarnera, F., Ortis, A., Puglisi, G., Paratore, A., Bui, L. M. Q., Fontani, M., Coccomini, D. A., Caldelli, R., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8100263 · Cited by 79
“Among all, one of the first effective techniques was the AttGAN, proposed by He et al. [7] with an attribute classification constraint applied in the latent representation of the generated image in order to guarantee only the correct modifications of the desired attributes.”
MethodInfluentialBabaei, R., Cheng, S. S. M., Duan, R., & Zhao, S. (2025) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan14010017 · Cited by 103
“Conventional deepfakes rely on techniques like face swapping [2], where one individual’s face is replaced with another, and puppet-master techniques [3], which animate static images to mimic the movements of a source.”
Masked Face Recognition with Generative Data Augmentation and Domain Constrained Ranking
Geng, M., Peng, P., Huang, Y., & Tian, Y. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413723 · Cited by 85
“Generative Adversarial Net (GAN) has become a powerful technique to perform unsupervised generation of new images and is extremely effective in many tasks, such as facial attribute editing [11, 19] and make up transfer [18].”
MethodStitch it in Time: GAN-Based Facial Editing of Real Videos
Tzaban, R., Mokady, R., Gal, R., Bermano, A. H., & Cohen‐Or, D. (2022) · SIGGRAPH Asia Conference Papers · doi:10.1145/3550469.3555382 · Cited by 110
“Many approaches suggested the editing of facial attributes in images [Choi et al. 2018; He et al. 2019; Lample et al. 2017; Liu et al. 2019; Mokady et al. 2019; Usman et al. 2019].”
Evading DeepFake Detectors via Adversarial Statistical Consistency
Hou, Y., Guo, Q., Huang, Y., Xie, X., Ma, L., & Zhao, J. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01181 · Cited by 76
“In face manipulation, StarGAN [5], STGAN [34], A3GAN [52], and AttGAN [21] are employed to edit and manipulate the attributes and expressions of human faces, such as changing the hair color, adding beards, wearing glasses or creating smiling faces.”
MethodWhere Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking
Demir, İ., & Ciftci, U. A. (2021) · ACM Symposium on Eye Tracking Research and Applications (ETRA) · doi:10.1145/3448017.3457387 · Cited by 86
Urban-GAN: An artificial intelligence-aided computation system for plural urban design
Quan, S. J. (2022) · Environment and Planning B Urban Analytics and City Science · doi:10.1177/23998083221100550 · Cited by 82
“In particular, the TensorFlow with the GPU support is used to implement the DCGAN with reference to the open-sourced codes from the work of He et al. (2019).”
MethodMastering Deepfake Detection: A Cutting-Edge Approach to Distinguish GAN and Diffusion-Model Images
Guarnera, L., Giudice, O., & Battiato, S. (2024) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3652027 · Cited by 74
“…real/pristine images collected from CelebA [30], FFHQ, 1 and ImageNet [38] datasets and synthetic data generated by 9 different GAN engines (AttGAN [21], CycleGAN [48], GDWCT [5], IMLE [29], ProGAN [24], StarGAN [6], StarGAN-v2 [7], StyleGAN [26], StyleGAN2 [27]), and 4 text-to-image DM…”
A Survey of Deep Facial Attribute Analysis
Zheng, X., Guo, Y., Huang, H., Li, Y., & He, R. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-020-01308-z · Cited by 83
“rsion MSSSIM [118] to estimate the structure distortion and the identity distance. All these measurements contribute to evaluating the high-level similarity of two face images. In addition, He et al. [44] use an Inception-ResNet [110] to train a face recognizer for measuring the identity preservation ability with rank…”
BackgroundMethodInfluentialA Systematic Survey of Regularization and Normalization in GANs
Li, Z., Usman, M., Tao, R., Xia, P., Wang, C., Chen, H., & Li, B. (2022) · ACM Computing Surveys · doi:10.1145/3569928 · Cited by 101
A literature review and perspectives in deepfakes: generation, detection, and applications
Dagar, D., & Vishwakarma, D. K. (2022) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-022-00241-w · Cited by 111
Local and Global Perception Generative Adversarial Network for Facial Expression Synthesis
Xia, Y., Zheng, W., Wang, Y., Yu, H. L., Dong, J., & Wang, F. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3074032 · Cited by 74
“The further evaluation is to compare the performance of the proposed LGP-GAN with the current state-of-the-art approaches including StarGAN [6], AttGAN [8] and GANimation [20].”
BackgroundMethodInfluentialProactive Deepfake Defence via Identity Watermarking
Zhao, Y., Liu, B., Ding, M., Liu, B., Zhu, T., & Yu, X. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00458 · Cited by 113
“Two attributes manipulation methods, i.e., AttGAN [16] and StarGAN2 [7], two identity swap methods, i.e., InfoSwap [13] and SimSwap [6], and two face anonymization approaches, namely CIAGAN [31] and DeepPrivacy [18] are employed in this experiment.”
MethodAn Investigation of the Effectiveness of Deepfake Models and Tools
Mukta, M. S. H., Ahmad, J., Raiaan, M. A. K., Islam, S., Azam, S., Ali, M. E., & Jonkman, M. (2023) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan12040061 · Cited by 84
“In ATT-GAN [35], a revolutionary technique, an attribute categorization constraint is added to the generated image to ensure that only the necessary characteristics are changed in the proper ways.”
MethodFakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
Huang, Y., Juefei-Xu, F., Wang, R., Guo, Q., Ma, L., Xie, X., Li, J., Miao, W., Liu, Y., & Pu, G. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413732 · Cited by 71
“ion, we give a more detailed discussion on the limitation of GAN-based methods and introduce our post-processing method. 3.1 Artifact of GAN-Based Image Generation For both partial image manipulation [11, 18, 34] and full image synthesis [29–31], the generator of GAN-based image generation method has a decoder amplifi…”
MethodInfluentialWang, R., Huang, Z., Chen, Z., Liu, L., Chen, J., & Wang, L. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/107 · Cited by 113
CMTS: A Conditional Multiple Trajectory Synthesizer for Generating Safety-Critical Driving Scenarios
Ding, W., Xu, M., & Zhao, D. X. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197145 · Cited by 85
GuidedStyle: Attribute knowledge guided style manipulation for semantic face editing
Hou, X., Zhang, X., Liang, H., Shen, L., Lai, Z., & Wan, J. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.10.017 · Cited by 73
Towards relatable explainable AI with the perceptual process
Zhang, W., & Lim, B. Y. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501826 · Cited by 67
“2) Counterfactual samples can be based on canonical (prototype) or critical (almost ambiguous) examples [46], such as feminizing male faces [32, 109] or changing a scene from day to night [117].”
BackgroundDeepFake detection with multi-scale convolution and vision transformer
Lin, H., Huang, W., Luo, W., & Lü, W. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103895 · Cited by 77
Mitigating Demographic Bias in Facial Datasets with Style-Based Multi-attribute Transfer
Georgopoulos, M., Oldfield, J. P., Nicolaou, M. A., Panagakis, Y., & Pantić, M. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01448-w · Cited by 83
“Along with our method, both StarGAN and AttGAN are capable of synthesizing a dataset with a distribution of labels close to uniform in the case of the binary attributes skin tone and gender.”
BackgroundMethodInfluentialTransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
Xu, Y., Yin, Y., Jiang, L., Wu, Q., Zheng, C., Loy, C. C., Dai, B., & Wu, W. (2022) · 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/cvpr52688.2022.00753 · Cited by 92
“These efforts have expedited the advancement in facial editing [15,17,43], an important downstream task with many practical applications, circum-venting the cumbersome manual editing processes.”
BackgroundBlendFace: Re-designing Identity Encoders for Face-Swapping
Shiohara, K., Yang, X., & Taketomi, T. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00702 · Cited by 137
“Recent advances in generative adversarial networks (GANs) [7, 25, 34, 36, 51, 58, 89] have enabled the photo-realistic image generation in various conditions, e.g ., attribute [29], identity [9], and expression [83], as well as unconditional image generation.”
BackgroundDeepfake detection using deep feature stacking and meta-learning
Naskar, G., Mohiuddin, S., Malakar, S., Cuevas, E., & Sarkar, R. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e25933 · Cited by 82
Attribute-Aware Generative Design With Generative Adversarial Networks
Yuan, C., & Moghaddam, M. (2020) · IEEE Access · doi:10.1109/access.2020.3032280 · Cited by 72
“AttGAN [27] is proven a successful model for editing facial images with respect to attributes such as ‘‘bald’’, ‘‘eyeglass’’, and ‘‘mustache’’.”
BackgroundMethodInfluentialL2M-GAN: Learning to Manipulate Latent Space Semantics for Facial Attribute Editing
Yang, G., Fei, N., Ding, M., Liu, G., Lu, Z., & Xiang, T. (2021) · 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/cvpr46437.2021.00297 · Cited by 85
“AttGAN [17] modeled the relation between attributes and the latent space learned by a GAN.”
BackgroundMethodDisentangled Image Generation Through Structured Noise Injection
Alharbi, Y., & Wonka, P. (2020) · 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/cvpr42600.2020.00518 · Cited by 61
The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage
Proença, H. P. M. C. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3066054 · Cited by 67
Face Editing Based on Facial Recognition Features
Ning, X., Xu, S., Nan, F., Zeng, Q., Wang, C., Cai, W., Li, W., & Jiang, Y. (2022) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2022.3182650 · Cited by 67
“To achieve accurate editing of face attributes, He et al. [5] took the source image and target attribute vector as input to ensure accurate editing by adding attribute classification constraints to generated images.”
BackgroundMethodMU-GAN: Facial Attribute Editing Based on Multi-Attention Mechanism
Zhang, K., Su, Y., Guo, X., Qi, L., & Zhao, Z. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2020.1003390 · Cited by 67
Wang, Y., Gao, Y., & Lian, Z. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392456 · Cited by 59
“In this section, we compare our method with existing methods of attribute-controllable image synthesis, including AttGAN [He et al. 2019], StarGAN [Choi et al. 2018], RelGAN [Wu et al. 2019] and STGAN [Liu et al. 2019 earliest works that address the problem of image attribute editing.”
BackgroundMethod
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.