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 801–848 of 848
Fair GANs through model rebalancing for extremely imbalanced class distributions
Jain, A., Memon, N. D., & Togelius, J. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11410860 · Cited by 3
“We report results on the FFHQ dataset in section 3.1 and on the imbalanced CIFAR10 dataset in section 3.2.”
InfluentialChen, Y., Lin, L., Ruan, H., Chen, Y., Zhong, S., & Zu, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131905
LiteCNN: A Lightweight Model for Face Recognition in Mask-Occluded Scenarios
Zhang, Q. (2025) · International Conference on Computer Communication, Networks and Information Science (CCNIS) · doi:10.1109/ccnis69465.2025.00087
“Techniques like GANs [13] and autoencoders [14] are commonly used .”
Pervin, M. T., Tavakkoli, A., Bebis, G. N., & Jiang, F. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6384649
A Knowledge-Guided Bi-Modal Network for the Classification of Anterior Chamber Angle Images
Jia, X., Huang, J., Nie, D., Guan, L., & Qiu, J. (2026) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2026.3677046
“[22]applyattributestochangethereconstructed image, such as changing red hair to black hair.”
CULTURAL ENTREPRENEURSHIP AND THE DIGITAL ECONOMY: EMERGING BUSINESS MODELS IN PERFORMING ARTS
Arasu, R., Dutta, M., Sharma, S., Jain, P., Kumar, V., Singh, P., & Kumar, B. (2026) · ShodhKosh Journal of Visual and Performing Arts · doi:10.29121/shodhkosh.v7.i2s.2026.7361
“It is necessary to know the interaction between these factors to develop resilient and inclusive business plan in the performing art sector He et al. (2019), Xi et al. (2023).”
Hou, S., Jiang, X., Xu, K., Xu, Q., Sun, T., & Meng, L. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3678982
“Face editing focuses on modifying specific facial characteristics while preserving the underlying identity [17], [18], [19].”
Improving Latent Representations of ConvNets for Visual Understanding
Robert, T. (2019) · theses.fr (ABES) · doi:10.70675/c3069ba0z2a64z48c3zbfa5zdf2d968df5fe · Cited by 1
Zhang, B. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3753
SDA-Det: A subpixel-aware dual-domain artifact detector for AI-generated image detection
Lü, P., Liang, K., Liu, X., Lu, X., & Li, A. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132304 · Cited by 4
Latent representations for facial images and video editing
Yao, X. (2022) · theses.fr (ABES) · doi:10.70675/36bff61dz9deaz4530z8f62zcfde241e26ad
Deep learning methods for visual content creation and understanding
Sbai, O. (2021) · theses.fr (ABES) · doi:10.70675/aa60bca2zdda6z45cazbd02z4275271c264c
A neural voice transformation framework for modification of pitch and intensity
Bous, F. (2023) · theses.fr (ABES) · doi:10.70675/5a1b2884z903dz4b97z8073z7614dbb58847 · Cited by 2
Designing Visual Explanations of Deep Learning Classifiers Decisions in Medical Image Analysis
Charachon, M. (2023) · theses.fr (ABES) · doi:10.70675/b98d6f58z1f2ez4c54z8572z10d87dd80397 · Cited by 1
GAN-based face image synthesis and its application to face recognition
Yin, X. (2022) · theses.fr (ABES) · doi:10.70675/6aef4315za3fbz4be8zab59z6f74668ca8fb
Optimal transport for transfer learning across spaces
Tran, Q. H. (2024) · theses.fr (ABES) · doi:10.70675/c924af75zce59z40c4z8c98z85e06505f70e
SCA-Det: A structure-context artifact detector for AI-generated image detection
Liang, K., Lu, P.-F., Liu, X., Lu, X., & Li, A. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133627 · Cited by 1
Synergistic multi-modal fusion for identity-preserving face aging via latent diffusion
Deng, C., Peng, Y., Huang, Y., Lei, R., Kin Tak, U., & Wang, W. (2026) · The Visual Computer · doi:10.1007/s00371-026-04473-3
FAE-Net: Fashion Attribute Editing via Disentangled Latent Conditioning in Diffusion Models
Bhargav, P. R., Bhattacharya, G., Vivek, B. S., & Gubbi, J. (2026) · IEEE Workshop/Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00027
“With recent advances in computer vision and generative modelling, numerous image editing works have been developed using GANs [7, 17, 22, 27] and Diffusion [19, 28, 33, 38] models.”
HiGlassRM: Learning to Remove High-prescription Glasses via Synthetic Dataset Generation
Lee, S., & Kim, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00445
“Learning-based methods [2–5, 7–10] leverage adversarial/multi-domain objectives and latent manipulations to edit attributes while partially preserving identity.”
An evaluation framework for generative face-editing methods: Quality, identity and disentanglement
Bour, L., Bougleux, S., Charrier, C., & Lézoray, O. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117582
Enhancing Deepfake Image Detection with Swin Transformer and Multi-Form Data Augmentation
Tripathi, M., Chaurasia, S., Chaurasia, P., Asim, M. A., & Pandey, S. (2026) · International Conference on Intelligent Processing, Hardware, Electronics, and Radio Systems (CIPHER) · doi:10.1109/cipher70417.2026.11523945
“Current methods can be broadly categorized into face swapping [7], facial reenactment [8], attribute manipulation [9], and full face synthesis [10].”
Mask-Guided Region-Specific Editing in Diffusion Models
Shaheryar, M., Park, J. M., & Jung, S. K. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4578-0_11
Huang, X., Wang, X., Wang, Q., Zhang, J., Xu, T., & Wang, Y. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106042 · Cited by 1
Yan, W., Xu, X., Zhang, Y., Xia, X., & Li, Y. (2026) · Electronic Research Archive · doi:10.3934/era.2026216
Almaimani, M., Li, X., Kider, J. T., Volonte, M., & Patterson, E. K. (2026) · Computer Animation and Virtual Worlds · doi:10.1002/cav.70150
“To enhance the fidelity of synthetic image generation, studies have introduced iterative training schemes [24], feature-focused emphasis during learning [25], and multiresolution architectures that utilize sub-generators to adapt the input images [26].”
Deepfake Detection: A Taxonomy with Structured Analysis ofvarious Approaches and Research ChallengesPreprint
Kaushik, T., & Singh, S. N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6981436
GROFF: A Generative Restoration Model for Occluded Face Filling
Xu, H., Wan, Z., & Wei, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1947-6_35
Portraitagent: verified multi-agent diffusion editing for identity-preserving portrait manipulation
Wen, L., & Feng, C. (2026) · The Visual Computer · doi:10.1007/s00371-026-04561-4
“Star-GAN [25] performed multi-domain translation with one generator, AttGAN [26] incorporated attribute supervision, and STGAN [27] used selective transfer units to mitigate entanglement.”
Sketch-to-color image generation using generative adversarial networks (GANs)
Kumar, T. S., Devi, S. G., Pavani, S., Kama, S., & Soujanya, G. (2026) · AIP conference proceedings · doi:10.1063/5.0342039
DeepWatch- A Real-Time Deepfake Video Detecting Browser Extension
Yadav, V., Singh, M., Kumari, S., Jadon, S., & Gupta, S. (2026) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/ic2pct68894.2026.11584455
FreqSeqNet: Dual-Domain Modeling for Sequential Face Manipulation Order Detection
Zhai, X., Geng, L., & Song, X. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3507-0_1
Realistic Facial Attribute Control via Variational Autoencoding
Caprita, B., & Spînu, S. (2026) · Journal of Military Technology · doi:10.32754/jmt.2026.1.06
“AttGAN [3] introduced an architecture that allows editing only the desired facial attributes while keeping other features unchanged.”
F-BAD: A frequency-driven black-box active defense framework against facial forgery
Chang, Q., Wang, Z., Liu, X., Chen, Y., Yao, Y., Li, X., & Zhao, Y. (2026) · Displays · doi:10.1016/j.displa.2026.103631
Multi-model active defense method for face forgery based on attribute-sensitive latent space
Jia, C., Liu, Y., Su, C., Zhou, Z., Liu, H., Li, Y., Zhu, H., & Xiao, Y. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123947
Xian, Y., Xue, S., Ma, B., & Qu, Y. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3722506
“In contrast, attribute editing methods, including StarGAN [28], AttGAN [29], and HISD [30], primarily focus on modifying local or global facial attributes without altering identity-related features.”
Suspicious Frequency Amplified Hybrid Framework for Generalizable AIGC Image Detection
Wang, J., Zou, J., Yu, Z., Ye, S., Wan, W., Gu, L., Zhou, J., & Zhang, W. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3723118
LucencyNet: A Generative Model for Translucency Editing from a Single Image
Wang, Y., & Li, H. (2026) · doi:10.1145/3810280.3810379
“Takingasingleimageandasemanticattribute oftheimageastheinputdata,anewimagewithvariedimage attributecanbegeneratedbyatrainedneuralnetwork[12].”
Boundary-guided frequency fusion for facial attribute editing forgery detection and localization
Gao, J., Hua, X., Shao, G., Chen, W., & Wei, K. (2026) · The Visual Computer · doi:10.1007/s00371-026-04720-7
A Novel Glow Adversarial Attack for Proactive Deepfake Defense
Bukhari, M., Maqsood, M., Lee, M. Y., & Rho, S. (2026) · IEEE Access · doi:10.1109/access.2026.3729265
“Deepfake generation techniques are classified into four types: full-face synthesis [29], [30], attribute manipulation [31], [32], [33], expression swap [34], [35], and identity switch [36], [37].”
InfluentialMFF-Net: Multi-view feature fusion network for AI-generated image detection
Zhang, H.-J., Tan, H., Qin, J.-H., & Yang, Z.-J. (2026) · Expert systems with applications · doi:10.1016/j.eswa.2026.134394 · Cited by 1
$$\mu $$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
Pontorno, O., Litrico, M., Guarnera, L., Giuffrida, M. V., & Battiato, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37422-6_20 · Cited by 1
FaceParts: Segmentation and Editing of Gaussian Splatting Avatars
Dolega, T., Farganus, J., Galus, D., Czachorowski, M., Syga, P., & Spurek, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-36871-3_12
Jiamin, 张. Z., Jing, 张. Z., & Xu, H. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop260784
GRAFF-MM : Graph-Frequency Filtering for Multi-Modal Memorability PredictionPreprint
Banna, T. T., Deb, S., Rahman, S., & Rahman, S. (2026) · Research Square · doi:10.21203/rs.3.rs-10283943/v1
Degradation-aware generative stereo image restoration
Chahi, A., Kas, M., & Ruichek, Y. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02739-3
“GANs have become a fundamental tool for a wide range of image generation tasks tailored to specific vision tasks, including image-to-image translation [3, 4], human pose synthesis [5], image fusion [6], and image editing [7, 8].”
Survey on intelligent video surveillance
Elnady, M., Abdelmunim, H. E., Abidou, D., & Elmadah, I. (2026) · Journal Of Big Data · doi:10.1186/s40537-026-01560-z
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.