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 401–500 of 848
The Current Landscape of Deepfake Legislation in the United States
Ugwuoke, V., & Sanfilippo, M. R. (2025) · Journal of Information Policy · doi:10.5325/jinfopoli.15.2025.0004 · Cited by 7
Distributor-centric model watermarking for image generative models
Fei, J., Dai, Y., Yang, W., & Xia, Z. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114422 · Cited by 9
ROFI: a deep learning-based ophthalmic sign-preserving and reversible patient face anonymizer
Tian, Y., Zhou, M., Chen, Y., Li, F., Qi, L., Wang, S., Xu, X., Yu, Y., Xu, S., Lei, C., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02062-7 · Cited by 13
SegTex: A Large Scale Synthetic Face Dataset for Face Recognition
Ambardi, L., Hong, S., & Park, I. K. (2023) · IEEE Access · doi:10.1109/access.2023.3336405 · Cited by 7
“Many studies have focused on creating specific parts of the face, such as hair [15], eyes [16], and mouth [17].”
Backgroundr-FACE: Reference guided face component editing
Deng, Q., Cao, J., Liu, Y., Li, Q., & Sun, Z. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110425 · Cited by 7
LEAT: Towards robust deepfake disruption in real-world scenarios via Latent Ensemble Attack
Shim, J., & Yoon, H. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127417 · Cited by 10
Unified Face Matching and Physical-Digital Spoofing Attack Detection
Kunwar, A., & Rattani, A. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00157 · Cited by 7
“Digital spoofing attacks based on facial manipulation based deepfakes depict human subjects with altered identities (identity swap) [44], attributes, or malicious actions and expressions (face reenactment) in a given image or a video [8, 18].”
Few-Shot Face Recognition: Leveraging GAN for Effective Data Augmentation
Li, S., Yue, C., & Zhou, H. (2025) · Electronics · doi:10.3390/electronics14102003 · Cited by 7
Translate the Facial Regions You Like Using Self-Adaptive Region Translation
Liu, W., Chen, W., Yang, Z., & Shen, L. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16316 · Cited by 7
“As shown in Fig.2(a), for image level translations approaches like Star-GAN(Choi et al. 2018), AttGAN(He et al. 2019) and FU-NIT(Liu et al. 2019), the same translation is usually applied to different face regions and they can only transfer the whole image from domain A to B .”
BackgroundAttention Based Facial Expression Manipulation
Wang, F., Xiang, S., Liu, T., & Fu, Y. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9456007 · Cited by 14
Attribute-Guided Target Data Separation Network for DAS VSP Data
Wang, S., Li, Y., & Zhao, Y. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3126022 · Cited by 7
“Refer to [45], we use an encoder–decoder architecture as the generation network G, a classifier C, and a discriminator D as the discriminator network and extract the four kinds of target data simultaneously through four GANs in parallel.”
MethodImproving Evaluation of Facial Attribute Prediction Models
Lingenfelter, B., & Hand, E. (2021) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg52635.2021.9667077 · Cited by 7
Knowledge Sharing for Pulmonary Nodule Detection in Medical Cyber-Physical Systems
Zhu, H., Han, G., Hou, J., Liu, X., & Ma, Y. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3220430 · Cited by 9
“Combining with adversarial loss ( (cid:4) adv ), focal loss ( (cid:4) fl ), attributive loss (cid:4) att [10], IoU loss (cid:4) iou , a hybrid objective loss for the generator G and discriminator D can be defined as where λ 1 and λ 2 are the empirical weights from the LSTM-based enthusiasm…”
BackgroundFace Recognition via Multi-Level 3D-GAN Colorization
Khan, Z., Umar, A. I., Shirazi, S. H., Shahzad, M., Assam, M., El-Wakad, M. T., & Attia, E.-A. (2022) · IEEE Access · doi:10.1109/access.2022.3226453 · Cited by 9
“[60] and worked as an attribute classifier and tried to guarantee the generation of correct faces based on desired facial attributes.”
BackgroundLearning Face Forgery Detection in Unseen Domain with Generalization Deepfake Detector
Tran, V.-N., Lee, S., Le, H.-S., Kim, B., & Kwon, K. (2023) · International Conference on Consumer Electronics · doi:10.1109/icce56470.2023.10043436 · Cited by 10
“Some remarkable researches of face manipulation can be mentioned as: AttGAN [10] added an attribute classification constraint to guarantee the accurate alteration of the required qualities in the final image and retain attribute excluding information.”
Background3D Generative Model Latent Disentanglement via Local Eigenprojection
Foti, S., Koo, B., Stoyanov, D. V., & Clarkson, M. J. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14793 · Cited by 13
Blemish-aware and Progressive Face Retouching with Limited Paired Data
Xie, L., Xue, W., Xu, Z., Wu, S., Yu, Z., & Wong, H. (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/cvpr52729.2023.00542 · Cited by 15
Gated SwitchGAN for Multi-Domain Facial Image Translation
Zhang, X., Zhu, Y., Chen, W., Liu, W., & Shen, L. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3074807 · Cited by 7
“Different from the previous works [11], [12], [27] that concatenate the input image or feature maps with their corresponding label, our label is regarded as a switch of different attribute features in the networks.”
BackgroundMethodInfluentialA GAN-based Approach to Communicative Gesture Generation for Social Robots
Tuyen, N. T. V., Elibol, A., & Chong, N. Y. (2021) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso51874.2021.9542828 · Cited by 7
Cross-Spectrum Thermal Face Pattern Generator
Cao, X., Lai, K., Hsu, G.-S. J., Smith, M. R., & Yanushkevich, S. N. (2022) · IEEE Access · doi:10.1109/access.2022.3144308 · Cited by 7
“Facial attribute editing task tries to manipulate one or more attributes of a given face image, while preserving its identity details [18].”
BackgroundSingle-Sample Face Recognition Based on Shared Generative Adversarial Network
Ding, Y., Tang, Z., & Wang, F. (2022) · Mathematics · doi:10.3390/math10050752 · Cited by 7
Deepfake Style Transfer Mixture: A First Forensic Ballistics Study on Synthetic Images
Guarnera, L., Giudice, O., & Battiato, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06430-2_13 · Cited by 11
“[15] proposed a new technique called AttGAN in which an attribute classification constraint is applied to the generated image, in order to guarantee only the correct modifications of the desired attributes.”
MethodGAN with Multivariate Disentangling for Controllable Hair Editing
Guo, X., Kan, M., Chen, T., & Shan, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19784-0_38 · Cited by 14
“Most face editing methods [19,22,4,27,14,7,5,17,23] manipulate specific face attributes by using binary attribute labels (e.g., with or without glasses/smiling).”
BackgroundSelf-citationPontorno, O., Guarnera, L., & Battiato, S. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-78305-0_12 · Cited by 6
Disrupting Deepfakes: A Survey on Adversarial Perturbation Techniques and Prevention Strategies
Bagaria, U., Kumar, V., Rajesh, T., Deepak, V., & Shylaja, S. S. (2024) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3669754.3669799 · Cited by 10
DC-BiNet: Towards interpretable generated image detection with dark channel prior
Tan, D., Niu, C., Yang, Y., Yang, D., & Tan, B. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127508 · Cited by 8
Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models
Lin, Z., Lin, H., Lin, L., Chen, S., & Liu, X. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104459 · Cited by 8
Forensic-MoE: Exploring Comprehensive Synthetic Image Detection Traces With Mixture of Experts
Fang, M., Li, Z., Yu, L. J., Yang, Q., Xie, H., & Zhang, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01651 · Cited by 17
“Recently, with the revolution of generative techniques like Generative Adversarial Networks (GANs) [5, 15, 18, 24, 25] and Diffusion Models [11, 19, 46, 50, 58], everyone is able to generate controllable and high-quality images without specific expertise.”
PattGAN: Pluralistic Facial Attribute Editing
Sun, Q., Guo, J., & Liu, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3185733 · Cited by 10
A controllable face forgery framework to enrich face-privacy-protection datasets
Yang, J., Zhu, Y. T., Xiao, S., Lan, G., & Li, Y. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104566 · Cited by 8
Double-Layer Search and Adaptive Pooling Fusion for Reference-Based Image Super-Resolution
Guo, K., Chen, L., Zhu, X., Kui, X., Zhang, J., & Shi, H. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3604937 · Cited by 6
“1 INTRODUCTION Image super-resolution aims to recover the real textures and natural structures of high-resolution (HR) images from low-resolution (LR) observations [12, 22, 44, 54].”
BackgroundText-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation
Wei, X., Xu, Z. T., Liu, C., Wu, S., Yu, Z., & Wong, H. (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/cvpr52729.2023.01848 · Cited by 7
Wang, W., Xiao, H., & Fang, Y. (2024) · International Journal of Clothing Science and Technology · doi:10.1108/ijcst-09-2023-0129 · Cited by 6
A deep dive into enhancing sharing of naturalistic driving data through face deidentification
Thapa, S., & Sarkar, A. (2024) · The Visual Computer · doi:10.1007/s00371-024-03552-7 · Cited by 9
Face forgery video detection based on expression key sequences
Tu, Y., Wu, J., Lu, L., Gao, S., & Li, M. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102142 · Cited by 7
Towards Sample-Specific Backdoor Attack With Clean Labels via Attribute Trigger
Zhu, M., Li, Y., Guo, J., Wei, T., Xia, S., & Qin, Z. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3552234 · Cited by 19
“Luckily, we can at least find some suitable attributes in image classification tasks, based on some recent studies [31], [63], [64].”
3-D Face De-Identification With Preserving Multi-Facial Attributes: A Benchmark
Liu, Y. M., Cheng, K. H. M., Savić, M., Chen, H., Yu, Z., & Zhao, G. (2025) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2025.3570599 · Cited by 11
Deep learning‐augmented radioluminescence imaging for radiotherapy dose verification
Jia, M. J., Yang, Y., Wu, Y., Li, X., Xing, L., & Wang, L. (2021) · Medical Physics · doi:10.1002/mp.15229 · Cited by 6
ShaTure: Shape and Texture Deformation for Human Pose and Attribute Transfer
Yu, W.-Y., Po, L.-M., Xiong, J., Zhao, Y., & Xian, P. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3157146 · Cited by 6
Latent Vector Prototypes Guided Conditional Face Synthesis
Wei, Q., Yang, X., Sang, T., Wang, H., Xiaofeng, Z., Cheng, Z., Zhao, Z., & Zeng, Z. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897502 · Cited by 6
“The outputs are not perfect, however, this is to be expected since face attributes are correlated as mentioned in previous works [9,10].”
BackgroundMethodResultInfluentialLin, Z., Xu, W., Ma, X., Xu, C., & Han, X. (2023) · Electronics · doi:10.3390/electronics12194111 · Cited by 6
Semantic Adversarial Attacks on Face Recognition Through Significant Attributes
Khedr, Y. M., Xiong, Y., & He, K. (2023) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-023-00376-6 · Cited by 8
“Recently, methods based on Generative Adversarial Network (GAN) have appeared that are used to manipulate facial attribute images, such as StarGAN [13], STGAN [14], and AttGAN [15].”
Distributionally Generative Augmentation for Fair Facial Attribute Classification
Zhang, F.-D., He, Q., Kuang, K., Liu, J.-S., Chen, L., Wu, C., Xiao, J., & Zhang, H. (2024) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr52733.2024.02151 · Cited by 16
“Generative models have achieved great success in recent years [11, 25, 45, 64, 69].”
Self-Attention-Masking Semantic Decomposition and Segmentation for Facial Attribute Manipulation
Xia, X., Yu, F., Li, N., Qu, Y., Zhang, J., & Zhu, C. (2020) · IEEE Access · doi:10.1109/access.2020.2974239 · Cited by 7
“Typical approaches such as StarGAN [3] and AttGAN [9] confirmed that only a pair of generator and discriminator is required for the face attribute manipulation, which can achieve remarkable translation effect.”
BackgroundMethodEvaluating Visual Properties via Robust HodgeRank
Xu, Q., Xiong, J., Cao, X., Huang, Q., & Yao, Y. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01438-y · Cited by 6
Continuous Learning of Face Attribute Synthesis
Ning, X., Li, W., Dong, X., Xu, S., Nan, F., & Yao, Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413141 · Cited by 8
“4 attributes, and could smoothly change between different TABLE I. ACCURACIES OF THE SYNTHETIC ATTRIBUTES OF DIFFERENT ALGORITHMS. natural happy angry fear sad surprise beard mouth eyebrow eye AttGAN[17] 0.49 0.56 0.51 0.43 0.49 0.45 0.52 0.47 0.40 0.43 StarGAN[9] 0.60 0.64 0.54 0.59 0.45 0.60 0.64 0.54 0.59 0.45 Styl…”
InfluentialHuang, Q., Zheng, Z., Hu, X., Sun, L., & Li, Q. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01436 · Cited by 6
“Star-GAN [7] and AttGAN [12] are two similar models for label-based synthesis.”
Generative Semantic Domain Adaptation for Perception in Autonomous Driving
Mukherjee, A., Joshi, A., Sharma, A., Hegde, C., & Sarkar, S. (2022) · Journal of Big Data Analytics in Transportation · doi:10.1007/s42421-022-00057-4 · Cited by 6
Disentangled face editing via individual walk in personalized facial semantic field
Lin, C., Xiong, S., & Lu, X. (2022) · The Visual Computer · doi:10.1007/s00371-022-02708-7 · Cited by 6
Unsupervised style-guided cross-domain adaptation for few-shot stylized face translation
Lan, J., Ye, F., Ye, Z., Xu, P., Ling, B. W., & Huang, G. (2022) · The Visual Computer · doi:10.1007/s00371-022-02719-4 · Cited by 6
Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features
Balakrishnan, G., Gadde, R., Martı́nez, A. M., & Perona, P. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19790-1_31 · Cited by 6
“Many of these so-called “conditional GANs” have been proposed, particularly for altering face attributes [2, 6, 9, 15, 20, 22–26, 34, 35, 42, 45], controlling face identity [6, 32–34], and conditioning on semantic maps [27, 40].”
BackgroundHairStyle Editing via Parametric Controllable Strokes
Song, X., Liu, C., Zheng, Y., Feng, Z., Li, L., Zhou, K., & Yu, X. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3241894 · Cited by 9
“Attribute-based facial image manipulation methods [3], [4], [5], [6], [45], [46], [47], [48], [49], [50], [51] change face appearances by controlling specific facial attributes, such as gender, age, expression, eyeglasses, and hair.”
BackgroundPlesh, R. O., Peer, P., & Štruc, V. (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/cvpr52729.2023.01616 · Cited by 9
“g, [28, 13], capable of adding glasses to an input face image.”
BackgroundDT-TransUNet: A Dual-Task Model for Deepfake Detection and Segmentation
Zheng, J., Zhou, Y., Hu, X., & Tang, Z. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8540-1_20 · Cited by 6
Facial Attribute Editing using Semantic Segmentation
Chen, P., Xiao, Q., Xu, J., Dong, X., & Sun, L. (2019) · International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS) · doi:10.1109/hpbdis.2019.8735455 · Cited by 7
“AttGAN [9] takes the relation between the attributes and the latent representation into account, and thus proposes a new framework based on encoder-decoder architecture.”
BackgroundMethodInfluentialAdaptive semantic attribute decoupling for precise face image editing
Ju, Y., Zhang, J., Mao, X., & Xu, J. (2021) · The Visual Computer · doi:10.1007/s00371-021-02198-z · Cited by 7
Mask Based Unsupervised Content TransferPreprint
Mokady, R., Benaim, S., Wolf, L., & Bermano, A. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.06558 · Cited by 7
“Others (Lample et al. (2017); He et al. (2019); Liu et al. (2019)) produce images in a target domain with a given attribute (e.g glasses), but such attribute is unique and not varying or controlled (e.g., not allowing the specification of a specific pair of glasses).”
BackgroundMethodInfluentialMorphy: A Datamorphic Software Test Automation ToolPreprint
Zhu, H., Bayley, I., Liu, D., & Zheng, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.09881 · Cited by 6
“In [29, 30], 200 images of different persons were used and each generated 13 mutants using GAN-Attr [13] to alter the facial features.”
MethodLEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack
Shim, J., & Yoon, H. (2023) · arXiv · doi:10.48550/arxiv.2307.01520 · Cited by 6
“Face attribute manipulation (Choi et al. 2018; He et al. 2019; Karras, Laine, and Aila 2019; Patash-nik et al. 2021; Preechakul et al. 2022) involves modifying specific facial attributes to achieve desired characteristics, such as altering hairstyles or expressions.”
DeepFeatureX-SN: Generalization of deepfake detection via contrastive learning
Pontorno, O., Guarnera, L., & Battiato, S. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-21060-1 · Cited by 16
“For the GAN models, images from AttGAN [31], BigGAN [32], Cycle - GAN [33 ], GauGAN [34], GDWCT [ 35 ], ProGAN [36], StarGAN [37], StyleGAN [ 38 ], StyleGAN2 [39] and StyleGAN3 [40] are included.”
Casu, M., Guarnera, L., Zangara, I., Caponnetto, P., & Battiato, S. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/9977058 · Cited by 5
Cassia, M., Guarnera, L., Casu, M., Zangara, I., & Battiato, S. (2025) · IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) · doi:10.1109/metroxraine66377.2025.11340536 · Cited by 11
“Synthetic data were produced using five widely used GAN models: AttGAN [33], GDWCT [34] and StarGAN [35] (trained on CelebA), as well as StyleGAN [36] and StyleGAN2 [37] (trained on FFHQ).”
Image style disentangling for instance-level facial attribute transfer
Guo, X., Kan, M., He, Z., Song, X., & Shan, S. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103205 · Cited by 5
Self-citationAudio-Visual Contrastive Pre-train for Face Forgery Detection
Zhao, H., Zhou, W., Chen, D., Zhang, W., Guo, Y., Cheng, Z., Yan, P., & Yu, N. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3651311 · Cited by 12
“According to the feature extraction types, current methods can be roughly categorized into two types: textural feature-based methods and semantic feature-based methods.”
IDGuard: Robust, General, Identity-Centric POI Proactive Defense Against Face Editing Abuse
Dai, Y., Fei, J., & Huang, F. (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/cvpr52733.2024.01134 · Cited by 12
Melouk, M. M., Shao, M., Basit, A., Abouzahir, C., Zhou, R., & Shafique, M. (2025) · IEEE Access · doi:10.1109/access.2025.3614455 · Cited by 9
“Facial Attribute Editing such as AttGAN [49] and SMGAN [50] focus on editing specific facial attributes like age, gender, or expression while retaining the overall coherence of the original face, allowing for controlled manipulation of facial characteristics.”
Hierarchical image-to-image translation with nested distributions modeling
Qiao, S., Wang, R., Shan, S., & Chen, X. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110058 · Cited by 6
Self-citationUsharani, B. (2021) · Advances in educational technologies and instructional design book series · doi:10.4018/978-1-7998-6474-5.ch009 · Cited by 6
The Framework of Cross-Domain and Model Adversarial Attack against Deepfake
Qiu, H., Du, Y., & Lu, T. (2022) · Future Internet · doi:10.3390/fi14020046 · Cited by 6
“For example, StarGAN [19], AttGAN [20] and STGAN [21 can translate the facial images in domains by setting different conditional variables, such . . . Finally”
BackgroundFair Facial Attribute Classification via Causal Graph-Based Attribute Translation
Kang, S., Kim, G., & Yoo, C. D. (2022) · Sensors · doi:10.3390/s22145271 · Cited by 6
“The conditional GAN algorithms [44,46–48], including AttGAN, require the desired attribute to generate the given facial image without consideration of the causal relationship.”
BackgroundMethodInfluentialKDDGAN: Knowledge-Guided Explicit Feature Disentanglement for Facial Attribute Editing
Wang, Y., Zhao, Q., Liu, Q., Wang, G., Yu, H. Z., Liu, L., & Leng, J. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3347274 · Cited by 6
“Leveraging a prior knowledge to constrain feature representations during the training enables to obtain explicit semantics [11], but current models simply concatenate the prior knowledge with the latent representation in dimension [12], [13].”
BackgroundMethodInfluentialConceptual and Hierarchical Latent Space Decomposition for Face Editing
Özkan, S., Özay, M., & Robinson, T. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00666 · Cited by 5
“Some studies focus on training auto-encoders using images as conditional information [17, 29, 23].”
BackgroundMethodSemantic prior guided fine-grained facial expression manipulation
Xue, T., Jin, Y., Zheng, D., & Liu, Y. K. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01401-7 · Cited by 5
Abbasian, M., Rajabzadeh, T., Moradipari, A., Aqajari, S. A. H., Lu, H., & Rahmani, A. M. (2024) · ACM Symposium on Applied Computing · doi:10.1145/3605098.3636158 · Cited by 5
Exposing the Forgery Clues of DeepFakes via Exploring the Inconsistent Expression Cues
Liu, J., Wang, L., Wang, R., Ke, J., Ye, X., & Wu, Y. (2025) · International Journal of Intelligent Systems · doi:10.1155/int/7945646 · Cited by 7
“Te attribute manipulation can modify simple facial attributes (e.g., hair color and smile) and retouch complex attributes (e.g., gender and age), such as StarGAN [18] and STGAN [19].”
Impact of Sunglasses on One-to-Many Facial Identification Accuracy
Tian, S., Wu, H., King, M. C., & Bowyer, K. W. (2025) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg61629.2025.11099126 · Cited by 5
“Existing face attribute editing methods could potentially be used to add sunglasses to a face image [13], [20], [11], [28].”
Dehazing with Offset Correction and a Weighted Residual Map
Su, C., Wang, W., Zhang, X., & Jin, L. (2020) · Electronics · doi:10.3390/electronics9091419 · Cited by 5
“Generative Adversarial Network (GAN) which has been made great progress in text-to-image synthesis [24], image-image translation [25] and other applications [26] was also applied for dehazing [27].”
Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance
Chen, J., Zhang, J., Sangineto, E., Chen, T., Fan, J., & Sebe, N. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00371 · Cited by 8
“Most works [3, 30, 14, 17, 18, 25, 2, 31, 9, 34, 15, 21] are based on GANs and have achieved impressive facial attribute manipulation results.”
BackgroundDualPathGAN: Facial reenacted emotion synthesis
Kong, J., Shen, H., & Huang, K. (2021) · IET Computer Vision · doi:10.1049/cvi2.12047 · Cited by 5
“AttGAN [17] and STGAN [18] design a network structure with skip‐connection [19] to deal with the facial attributes synthesis task.”
MethodLearning Non-Linear Disentangled Editing For Stylegan
Yao, X., Newson, A., Gousseau, Y., & Pierre Hellier, J. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506060 · Cited by 5
A Comparative Study of Cross-Model Universal Adversarial Perturbation for Face Forgery
Lin, S.-Y., Chen, J.-C., & Wang, J. (2022) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip56404.2022.10008794 · Cited by 6
“We set the weight λ i , i = 1 . . . 4 as 0.8, 1, 8, 1.2 respectively for StarGAN, AggGAN, ATTGAN, and HiSD (The weights are obtained through experiments).”
MethodInfluentialYan, L., Kao, C.-W., Hwang, B., Chen, H., & Huang, H.-C. (2023) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001423590127 · Cited by 6
Face Attribute Modification Using Fine-Tuned Attribute-Modification Network
Islam, N. U., & Park, J. (2020) · Electronics · doi:10.3390/electronics9050743 · Cited by 5
“(a) Fine-tuned attribute modification network (FTAMN) (proposed approach); (b) Attribute GAN (AttGAN) [6]; (c) Facial attribute modification network (FAMN) [30].”
BackgroundResultInfluentialA novel attribute-based generation architecture for facial image editing
Li, D., Zhang, M., Zhang, L., Chen, W., & Feng, G. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09858-7 · Cited by 8
Scalable balanced training of conditional generative adversarial neural networks on image data
Pasini, M. L., Gabbi, V., Yin, J., Perotto, S., & Laanait, N. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-03808-2 · Cited by 5
“For instance, recent applications of GANs are related to video synthesis [5] to improve the resolution of videos generated through videocameras, and face image alteration [6] to help national security agencies identify fugitive criminals that undergo mild facial surgeries.”
BackgroundEGGAN: Learning Latent Space for Fine-Grained Expression Manipulation
Tang, J., Shao, Z., & Ma, L. (2021) · IEEE Multimedia · doi:10.1109/mmul.2021.3061544 · Cited by 8
MDVA-GAN: multi-domain visual attribution generative adversarial networks
Nawaz, M., Al-Obeidat, F. N., Tubaishat, A., Zia, T., Maqbool, F., & Rocha, Á. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-06969-0 · Cited by 7
“In the literature, StarGAN [13], StarGAN v2 [14], AttGAN [15], Fashion-AttGAN [16], and STGAN [17] are non-VA, but multi-domain generative models that are used for human face attributes (e.”
BackgroundOAW-GAN: occlusion-aware warping GAN for unified human video synthesis
Wei, D., Huang, K., Ma, L., Hua, J., Lai, B., & Shen, H. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03527-y · Cited by 5
InfoScrub: Towards Attribute Privacy by Targeted ObfuscationPreprint
Wang, H., Orekondy, T., & Fritz, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.10329 · Cited by 6
“, changing emotions in faces) [4, 13, 8, 1] in images.”
BackgroundSemantic Text-to-Face GAN -ST^2FGPreprint
Oza, M., Chanda, S., & Doermann, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.10756 · Cited by 6
Liu, S., Kailkhura, B., Zhang, J., Hiszpanski, A. M., Robertson, E. L., Loveland, D., & Han, T. Y.-J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08631 · Cited by 6
“, attGAN [32]) take an input image along with the attributes A that describe the desirable changes (G(I,A)).”
BackgroundMethodInfluentialAttribute-guided face adversarial example generation
Gan, Y., Xiao, X., & Xiang, T. (2024) · The Visual Computer · doi:10.1007/s00371-024-03265-x · Cited by 4
“For facial attribute manipulation, [27–29] leverage GANs and the encoder–decoder structure to achieve the desired results of attribute editing.”
Ai-Driven Advances and Challenges in Deepfake Technology: A Comprehensive Review
Patel, K. J. (2024) · Journal of Electrical Systems · doi:10.52783/jes.7451 · Cited by 4
“It guarantees accurate attribute alterations while maintaining other information by directly applying attribute classification limitations to generated images(He et al., 2019).”
Robust manipulated media localization and detection based on high frequency and texture features
Jiang, Q., Liu, S., Miao, S., Yi, H., Jin, X., Kou, Y., & Duan, H. (2025) · Discover Computing · doi:10.1007/s10791-025-09500-w · Cited by 7
“STGAN [48] took the difference between target and source attribute vectors as the input, and modified the encoder matrix to the encoder-decoder.”
Fang, Z., Jin, B., Yao, Z., Xiong, J., Wang, X., Lu, Z., & Lin, J. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112769 · Cited by 4
Yi, H., Jiang, Q., Huang, H., Tang, L., Yao, S., Lee, S., & Jin, X. (2026) · IEEE Transactions on Biometrics Behavior and Identity Science · doi:10.1109/tbiom.2026.3656922 · Cited by 4
“Notable achievements in this field include StarGAN [37] and STGAN [38], both of which demonstrate substantial technical strengths.”
Toward Robust Proactive Deepfake Detection via Orthogonal Moment Watermarking
Wang, C., Xu, X., Zhang, S., Ma, B., Li, Q., Liu, Y., & Xia, Z. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3692272 · Cited by 6
“Deepfake attacks include SimSwap [39], HiSD [40], AttGAN [41], and DeepPrivacy [42].”
Facial attribute editing method combined with parallel GAN for attribute separation
Wei, J. J., & Wang, W. (2023) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2023.104031 · Cited by 4
A Synergistic MOEA Algorithm with GANs for Complex Data Analysis
Qian, W., Xu, H., Chen, H., Yang, L., Lin, Y., Xu, R., Yang, M., & Liao, M. (2024) · Mathematics · doi:10.3390/math12020175 · Cited by 4
Hasan, M. M., & Nasrabadi, N. M. (2023) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb57857.2023.10448749 · Cited by 5
“Recently, with the development of generative adversarial networks (GANs) [6] and transformers [33], text-to-face synthesis [34, 31], and facial attribute editing [9, 35] with textual descriptions have gained increasing popularity.”
Background
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.