A survey on face data augmentation for the training of deep neural networks
Open accessThe DOI matches its Crossref record; 114 of the 114 references it cites were found in a registry or an index.
Abstract
The quality and size of training set have a great impact on the results of deep learning-based face-related tasks. However, collecting and labeling adequate samples with high-quality and balanced distributions still remains a laborious and expensive work, and various data augmentation techniques have thus been widely used to enrich the training dataset. In this paper, we review the existing works of face data augmentation from the perspectives of the transformation types and methods, with the state-of-the-art approaches involved. Among all these approaches, we put the emphasis on the deep learning-based works, especially the generative adversarial networks which have been recognized as more powerful and effective tools in recent years. We present their principles, discuss the results and show their applications as well as limitations. Different evaluation metrics for evaluating these approaches are also introduced. We point out the challenges and opportunities in the field of face data augmentation and provide brief yet insightful discussions.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Data augmentation is one of the effective methods to generate augmented views in SSCL [47], [193].”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [193]
Experimental — accuracy not yet measured
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
Image-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×
“For example, [110] improved the training techniques to encourage convergence of the GANs game, [111] applied Wasserstein distance and improved the stability of learning, Conditional GANs could determine the specific representation of the generated images by feeding the condition to both the generator and discriminator…”
MethodFaceNet: 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×
“The remarkable work by Facebook [1] and Google [2] demonstrated the effectiveness of large-scale datasets on obtaining high-quality trained model, and revealed that deep learning strongly relies on large and complex training sets to generalize well in unconstrained settings.”
BackgroundA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 1×
“Karras et al. [62] redesigned the generator architecture of GANs and proposed a style-based generator.”
BackgroundPerceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283 · cited 1×
“They employed the method proposed in the study of [58] to calculate the perceptual loss and extracted identity features through a face recognition module, e.g., VGG-Face [107] or Light CNN [145].”
MethodConditional Generative Adversarial Nets
Mirza, M., & Osindero, S. (2014) · arXiv · doi:10.48550/arxiv.1411.1784 · Cited by 8,863 · cited 1×
“…training techniques to encourage convergence of the GANs game, [6] applied Wasserstein distance and improved the stability of learning, Conditional GANs could determine the specific representation of the generated images by feeding the condition to both the generator and discrimi-nator [56, 101].”
MethodDeep Learning Face Attributes in the Wild
Liu, Z., Luo, P., Wang, X., & Tang, X. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.425 · Cited by 7,747
Self-citationImproved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965 · cited 2×
“For example, [110] improved the training techniques to encourage convergence of the GANs game, [111] applied Wasserstein distance and improved the stability of learning, Conditional GANs could determine the specific representation of the generated images by feeding the condition to both the generator and discriminator…”
MethodDeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 2×
“The remarkable work by Facebook [1] and Google [2] demonstrated the effectiveness of large-scale datasets on obtaining high-quality trained model, and revealed that deep learning strongly relies on large and complex training sets to generalize well in unconstrained settings.”
BackgroundParkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479 · cited 1×
“VGG-Face [144] or Light CNN [145].”
Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.927467 · Cited by 5,409
Research works printed but not linked: 50
- Alhaija HA, Mustikovela SK, Mescheder L, Geiger A, Rother C (2017) Augmented reality meets deep learning for car instance segmentation in urban scenes. In: British machine vision conference, vol 1, p 2
- Antoniou A, Storkey A, Edwards H (2017) Data augmentation generative adversarial networks. ArXiv preprint arXiv:1711.04340 · arXiv
- Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning, pp 214–223
- Banerjee S, Scheirer WJ, Bowyer KW, Flynn, PJ (2018) On hallucinating context and background pixels from a face mask using multi-scale gans. ArXiv preprint arXiv:1811.07104 · arXiv
- Blanz V, Vetter T et al (1999) A morphable model for the synthesis of 3d faces. Siggraph 99:187–194
- Cao J, Hu Y, Yu B, He R, Sun Z (2018) Load balanced gans for multi-view face image synthesis. ArXiv preprint arXiv:1802.07447 · arXiv
- Cao J, Hu Y, Zhang H, He R, Sun Z (2018) Learning a high fidelity pose invariant model for high-resolution face frontalization. In: Advances in neural information processing systems, pp 2872–2882
- Chen W, Xie X, Jia X, Shen L (2018) Texture deformation based generative adversarial networks for face editing. ArXiv preprint arXiv:1812.09832 · arXiv
- Chen X, Duan Y, Houthooft R, Schulman J, Sutskever I, Abbeel P (2016) Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In: Advances in neural information processing systems, pp 2172–2180
- Crispell D, Biris O, Crosswhite N, Byrne J, Mundy JL (2017) Dataset augmentation for pose and lighting invariant face recognition. ArXiv preprint arXiv:1704.04326 · arXiv
- Das D, Lee CSG (2018) Graph matching and pseudo-label guided deep unsupervised domain adaptation. In: International conference on artificial neural networks, pp 342–352
- Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680
- Gu G, Kim ST, Kim K, Baddar WJ, Ro YM (2017) Differential generative adversarial networks: synthesizing non-linear facial variations with limited number of training data. ArXiv preprint arXiv:1711.10267 · arXiv
- Gulrajani I, Kumar K, Ahmed F, Taiga AA, Visin F, Vazquez D, Courville A (2016) Pixelvae: a latent variable model for natural images. ArXiv preprint arXiv:1611.05013 · arXiv
- Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in neural information processing systems, pp 6626–6637
- Huang H, He R, Sun Z, Tan T et al (2018) Introvae: introspective variational autoencoders for photographic image synthesis. In: Advances in neural information processing systems, pp 52–63
- Huang H, Yu PS, Wang C (2018) An introduction to image synthesis with generative adversarial nets. ArXiv preprint arXiv:1803.04469 · arXiv
- Juefei-Xu F, Dey R, Bodetti V, Savvides M (2018) Rankgan: a maximum margin ranking gan for generating faces. In: Proceedings of the Asian conference on computer vision (ACCV), vol 4
- Karras T, Aila T, Laine S, Lehtinen J (2018) Progressive growing of gans for improved quality, stability, and variation. In: ICLR
- Kim T, Kim B, Cha M, Kim J (2017) Unsupervised visual attribute transfer with reconfigurable generative adversarial networks. ArXiv preprint arXiv:1707.09798 · arXiv
- Kingma DP, Dhariwal P (2018) Glow: Generative flow with invertible 1x1 convolutions. In: Advances in neural information processing systems, pp 10236–10245
- Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: Proceedings of the 2nd international conference on learning representations (ICLR)
- Kortylewski A, Schneider A, Gerig T, Egger B, Morel-Forster A, Vetter T (2018) Training deep face recognition systems with synthetic data. ArXiv preprint arXiv:1802.05891 · arXiv
- Kulkarni TD, Whitney WF, Kohli P, Tenenbaum J (2015) Deep convolutional inverse graphics network. In: Advances in neural information processing systems, pp 2539–2547
- Lample G, Zeghidour N, Usunier N, Bordes A, Denoyer L et al (2017) Fader networks: manipulating images by sliding attributes. In: Advances in neural information processing systems, pp 5967–5976
- Larsen ABL, Sønderby SK, Larochelle H, Winther O (2015) Autoencoding beyond pixels using a learned similarity metric. In: 33rd International conference on machine learning
- Li M, Zuo W, Zhang D (2016) Deep identity-aware transfer of facial attributes. ArXiv preprint arXiv:1610.05586 · arXiv
- Liu L, Xing J, Liu S, Xu H, Zhou X, Yan S (2014) Wow! you are so beautiful today!. ACM Trans Multimed Comput Commun Appl (TOMM) 11(1s):20
- Liu MY, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. In: Advances in neural information processing systems, pp 700–708
- Liu MY, Tuzel O (2016) Coupled generative adversarial networks. In: Advances in neural information processing systems, pp 469–477
- Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2015) Adversarial autoencoders. ArXiv preprint arXiv:1511.05644 · arXiv
- Masi I, Trãn AT, Hassner T, Leksut JT, Medioni G (2016) Do we really need to collect millions of faces for effective face recognition? In: European conference on computer vision. Springer, pp 579–596
- Moniz JRA, Beckham C, Rajotte S, Honari S, Pal C (2018) Unsupervised depth estimation, 3d face rotation and replacement. In: Advances in neural information processing systems, pp 9759–9769
- Pham HX, Wang Y, Pavlovic V (2018) Generative adversarial talking head: Bringing portraits to life with a weakly supervised neural network. ArXiv preprint arXiv:1803.07716 · arXiv
- Qiao F, Yao N, Jiao Z, Li Z, Chen H, Wang H (2018) Geometry-contrastive gan for facial expression transfer. ArXiv preprint arXiv:1802.01822 · arXiv
- Radford A, Metz L, Chintala S (2015) Unsupervised representation learning with deep convolutional generative adversarial networks. ArXiv preprint arXiv:1511.06434 · arXiv
- Sanchez E, Valstar M (2018) Triple consistency loss for pairing distributions in gan-based face synthesis. ArXiv preprint arXiv:1811.03492 · arXiv
- Shen Y, Zhou B, Luo P, Tang X (2018) Facefeat-gan: a two-stage approach for identity-preserving face synthesis. ArXiv preprint arXiv:1812.01288 · arXiv
- Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. In: Advances in neural information processing systems, pp 3483–3491
- Van den Oord A, Kalchbrenner N, Espeholt L, Vinyals O, Graves A et al (2016) Conditional image generation with pixelcnn decoders. In: Advances in neural information processing systems, pp 4790–4798
- Van Den Oord A, Kalchbrenner N, Kavukcuoglu K (2016) Pixel recurrent neural networks. In: Proceedings of the 33rd international conference on international conference on machine learning-volume 48, ICML’16. JMLR.org, pp 1747–1756
- Volpi R, Namkoong H, Sener O, Duchi JC, Murino V, Savarese S (2018) Generalizing to unseen domains via adversarial data augmentation. In: Advances in neural information processing systems, pp 5334–5344
- Wang Z, Tang X, Luo W, Gao S (2018) Face aging with identity-preserved conditional generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7939–7947
- Xiao T, Hong J, Ma J (2018) Dna-gan: learning disentangled representations from multi-attribute images. In: International conference on learning representations workshop 2018
- Yeh R, Liu Z, Goldman DB, Agarwala A (2016) Semantic facial expression editing using autoencoded flow. ArXiv preprint arXiv:1611.09961 · arXiv
- Zhao J, Cheng Y, Cheng Y, Yang Y, Zhao F, Li J, Liu H, Yan S, Feng J (2019) Look across elapse: disentangled representation learning and photorealistic cross-age face synthesis for age-invariant face recognition. Proc AAAI Conf Artif Intell 33:9251–9258
- Zhao J, Xiong L, Jayashree PK, Li J, Zhao F, Wang Z, Pranata PS, Shen PS, Yan S, Feng J (2017) Dual-agent gans for photorealistic and identity preserving profile face synthesis. In: Advances in neural information processing systems, pp 66–76
- Zhu H, Zhou Q, Zhang J, Wang JZ (2018) Facial aging and rejuvenation by conditional multi-adversarial autoencoder with ordinal regression. ArXiv preprint arXiv:1804.02740 · arXiv
- Zhu J.Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232
- Zhu X, Lei Z, Yan J, Yi D, Li SZ (2015) High-fidelity pose and expression normalization for face recognition in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 787–796
Cited by
Data augmentation: A comprehensive survey of modern approaches
Mumuni, A., & Mumuni, F. (2022) · Array · doi:10.1016/j.array.2022.100258 · Cited by 891
A Survey of Data Augmentation Approaches for NLP
Feng, S., Gangal, V., Wei, J., Chandar, S., Vosoughi, S., Mitamura, T., & Hovy, E. (2021) · Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 · doi:10.18653/v1/2021.findings-acl.84 · Cited by 670
A Comprehensive Survey of Image Augmentation Techniques for Deep Learning
Xu, M., Yoon, S., Fuentes, A., & Park, D. S. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109347 · Cited by 634
“First, we do not confine ourselves to a specific type of image, such as facial images [8].”
BackgroundSynthetic Data for Deep Learning
Nikolenko, S. I. (2021) · Springer Optimization and Its Applications · doi:10.1007/978-3-030-75178-4 · Cited by 423
Data Augmentation for Graph Neural Networks
Zhao, T., Liu, Y., Neves, L., Woodford, O., Jiang, M., & Shah, N. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17315 · Cited by 346
Data Augmentation techniques in time series domain: a survey and taxonomy
Iglesias, G., Talavera, E., González-Prieto, Á., Mozo, A., & Gómez-Canaval, S. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08459-3 · Cited by 347
“Some authors [124] tend to differentiate between DA and data generation due to the great advances made in NN models.”
BackgroundA Systematic Review on Data Scarcity Problem in Deep Learning: Solution and Applications
Bansal, M. A., Sharma, D. R., & Kathuria, D. M. (2022) · ACM Computing Surveys · doi:10.1145/3502287 · Cited by 306
“A survey on face data augmentation for the training of deep neural networks [Xiang Wang et al. 2020] To study various data for face related tasks It gives an outline of how to do face augmentation and what it can do.”
BackgroundImage Data Augmentation Approaches: A Comprehensive Survey and Future Directions
Kumar, T., Brennan, R., Mileo, A., & Bendechache, M. (2024) · IEEE Access · doi:10.1109/access.2024.3470122 · Cited by 287
“For instance, Wang et al. [32] explored and compared traditional data augmentation techniques [31], which include foundational techniques such as rotation, flipping, scaling, and cropping, widely used in various computer vision tasks.”
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
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“Data augmentation is one of the effective methods to generate augmented views in SSCL [47], [193].”
MethodA Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
Cui, Y., Liu, Z., & Lian, S. (2023) · IEEE Access · doi:10.1109/access.2023.3282993 · Cited by 207
“To overcome the limitation of insufficient data, augmentation algorithms [127], [128] have been widely used in deep learning scheme.”
Self-citationA Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images
Cui, Y., Liu, Z., & Lian, S. (2022) · arXiv · doi:10.48550/arxiv.2204.11161 · Cited by 154
“The survey [126] investigates data augmentation methods, particularly putting the emphasis on the deep learning-based works.”
BackgroundMethodSelf-citationAdvances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets
Kopalidis, T., Solachidis, V., Vretos, N., & Daras, P. (2024) · Information · doi:10.3390/info15030135 · Cited by 247
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
Ding, B., Liu, L., Bing, L., Kruengkrai, C., Nguyen, T. H., Joty, S., Si, L., & Miao, C. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.488 · Cited by 157
Generative Adversarial Networks for Face Generation: A Survey
Kammoun, A., Slama, R., Tabia, H., Ouni, T., & Abid, M. (2023) · ACM Computing Surveys · doi:10.1145/3527850 · Cited by 132
“Among popular works, some works [82, 137] showed that adding generated data to a small database increases performance by 15%.”
BackgroundTabular and latent space synthetic data generation: a literature review
Fonseca, J., & Bação, F. (2023) · Journal Of Big Data · doi:10.1186/s40537-023-00792-7 · Cited by 221
“[13] review Generative Adversarial Network architectures for medical imaging [29].”
BackgroundA Survey of Synthetic Data Augmentation Methods in Machine Vision
Mumuni, A., Mumuni, F., & Gerrar, N. K. (2024) · Machine Intelligence Research · doi:10.1007/s11633-022-1411-7 · Cited by 201
“Wang et al. [309], for example, reported several instances where models trained on synthetic data achieve better results on face recognition tasks.”
BackgroundFidora: Robust WiFi-Based Indoor Localization via Unsupervised Domain Adaptation
Chen, X., Li, H., Zhou, C., Liu, X., Wu, D., & Dudek, G. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3163391 · Cited by 149
Face recognition in unconstrained environment with CNN
Fredj, H. B., Bouguezzi, S., & Souani, C. (2020) · The Visual Computer · doi:10.1007/s00371-020-01794-9 · Cited by 137
“Also, various methods have been proposed to transform a real face image to a new type, such as pose transfer, hairstyle transfer, expression transfer, makeup transfer, and age transfer [30].”
MethodRaiaan, M. A. K., Fatema, K., Khan, I. U., Azam, S., Rashid, M. R. U., Mukta, M. S. H., Jonkman, M., & Boer, F. D. (2023) · IEEE Access · doi:10.1109/access.2023.3272228 · Cited by 138
“It only modifies the images’ color and lighting while preserving their geometry [65], [66].”
BackgroundA novel method based on machine vision system and deep learning to detect fraud in turmeric powder
Jahanbakhshi, A., Abbaspour‐Gilandeh, Y., Heidarbeigi, K., & Momeny, M. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104728 · Cited by 92
Li, M., Ma, X., Chen, C., Yuan, Y., Zhang, S., Yan, Z., Chen, C., Chen, F., Bai, Y., Zhou, P., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3071057 · Cited by 106
“For improving the generalization performance of the model, this study took an average of 1-2 pathological tissue sections from each patient as the research object, and finally selected 121 histopathological images [19], [20].”
MethodWheat ear counting using K-means clustering segmentation and convolutional neural network
Xu, X., Li, H., Yin, F., Xi, L., Qiao, H., Ma, Z., Shen, S., Jiang, B., & Ma, X. (2020) · Plant Methods · doi:10.1186/s13007-020-00648-8 · Cited by 90
“To provide sufficient data for model training, 12,000 augmented images of non-wheat ear, one wheat ear, two wheat ears, and three wheat ears were produced by randomly cutting, flipping, rotating, and adjusting the brightness of the original image [29–31].”
BackgroundUhlig, S., Alkhasli, I., Schubert, F. M., Tschöpe, C., & Wolff, M. (2023) · Ultrasonics · doi:10.1016/j.ultras.2023.107041 · Cited by 107
A multi-stage data augmentation and AD-ResNet-based method for EPB utilization factor prediction
Yu, H., Sun, H., Tao, J., Qin, C., Xiao, D., Jin, Y., & Liu, C. (2023) · Automation in Construction · doi:10.1016/j.autcon.2022.104734 · Cited by 87
Wang, B., Deng, J., & Jiang, H. (2022) · Foods · doi:10.3390/foods11152210 · Cited by 73
“In this case, data augmentation techniques are a good choice [31].”
BackgroundSmall Object Detection Method Based on Global Multi-Level Perception and Dynamic Region Aggregation
Zhu, Z., Zheng, R., Qi, G., Li, S., Li, Y., & Gao, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3402097 · Cited by 82
“However, data augmentation requires special optimization for object features, and improperly designed data augmentation strategies may introduce new noise and negatively affect the performance of feature extraction [27].”
BackgroundFiDo: Ubiquitous Fine-Grained WiFi-based Localization for Unlabelled Users via Domain Adaptation
Chen, X., Li, H., Zhou, C., Liu, X., Wu, D., & Dudek, G. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380091 · Cited by 87
“It is commonly used for image classification tasks [24, 39] and has also shown its effectiveness for several other applications including machine fault detection [32] and recommendation [37].”
GAN-Based Facial Attribute Manipulation
Liu, Y., Li, Q., Deng, Q., Sun, Z., & Yang, M. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3298868 · Cited by 72
“Moreover, FAM is also discussed in [44] and [45], but the main themes are on data augmentation and DeepFake detection, respectively.”
BackgroundSurvey on Videos Data Augmentation for Deep Learning Models
Cauli, N., & Recupero, D. R. (2022) · Future Internet · doi:10.3390/fi14030093 · Cited by 64
Smart UAV-assisted rose growth monitoring with improved YOLOv10 and Mamba restoration techniques
Zhao, F., Ren, Z., Wang, J., Wu, Q., Xi, D., Shao, X., Liu, Y., Chen, Y., & Mizuno, K. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100730 · Cited by 65
Computer-Aided Diagnosis and Staging of Pancreatic Cancer Based on CT Images
Li, M., Nie, X., Reheman, Y., Huang, P., Zhang, S., Yuan, Y., Chen, C., Yan, Z., Chen, C., Lv, X., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3012967 · Cited by 50
“To improve model generalization ability, we selected 3 cross-sectional images of plain CT scans with significant features from each CT sequence on average [27], [34], [35].”
MethodGPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation
Luo, J., Lei, W., Hou, F., Wang, C., Ren, Q., Zhang, S., Luo, S., Wang, Y., & Xu, L. (2021) · Electronics · doi:10.3390/electronics10111269 · Cited by 42
Balaha, H. M., Balaha, M. H., & Ali, H. A. (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102156 · Cited by 42
“Noise can help in that too by applying Gaussian noise [88].”
BackgroundVisual Deepfake Detection: Review of Techniques, Tools, Limitations, and Future Prospects
Ur Rehman Ahmed, N., Badshah, A., Adeel, H., Tajammul, A., Daud, A., & Alsahfi, T. (2025) · IEEE Access · doi:10.1109/access.2024.3523288 · Cited by 45
Greco, A., Saggese, A., Vento, M., & Vigilante, V. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05981-0 · Cited by 40
“During the training process, every sample image is perturbed using one of more random augmentation policies [59].”
MethodGenerative Adversarial Networks in Human Emotion Synthesis: A Review
Hajarolasvadi, N., Ramírez, M. A., Beccaro, W., & Demirel, H. (2020) · IEEE Access · doi:10.1109/access.2020.3042328 · Cited by 42
“A fine source of such approaches can be found in [134].”
BackgroundA Survey on Synthetic Biometrics: Fingerprint, Face, Iris and Vascular Patterns
Makrushin, A., Uhl, A., & Dittmann, J. (2023) · IEEE Access · doi:10.1109/access.2023.3250852 · Cited by 44
“An exhaustive review of face data augmentation approaches is presented in [15].”
BackgroundAbayomi‐Alli, O., Damaševičius, R., Maskeliūnas, R., & Misra, S. (2021) · Electronics · doi:10.3390/electronics10080978 · Cited by 33
Review of Image Augmentation Used in Deep Learning-Based Material Microscopic Image Segmentation
Ma, J., Hu, C., Zhou, P., Jin, F., Wang, X., & Huang, H. (2023) · Applied Sciences · doi:10.3390/app13116478 · Cited by 46
Self-citationOn the Generalization Ability of Data-Driven Models in the Problem of Total Cloud Cover Retrieval
Krinitskiy, M., Aleksandrova, M., Verezemskaya, P., Gulev, S., Sinitsyn, А. V., Kovaleva, N., & Gavrikov, A. (2021) · Remote Sensing · doi:10.3390/rs13020326 · Cited by 29
Generative Adversarial Networks-Based Imbalance Learning in Software Aging-Related Bug Prediction
Chouhan, S. S., & Rathore, S. S. (2021) · IEEE Transactions on Reliability · doi:10.1109/tr.2021.3052510 · Cited by 27
“There have been a lot of work done in synthetic data generation for image data [45]–[48].”
BackgroundFrontiers and developments of data augmentation for image: From unlearnable to learnable
Gan, L., Jiang, J., Bai, J., Su, Y., Su, Z., & Liu, H. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102660 · Cited by 31
Tie, J., & Wu, W. (2024) · International Journal of Rock Mechanics and Mining Sciences · doi:10.1016/j.ijrmms.2024.105784 · Cited by 22
Haq, E., Huang, J.-J., Li, K., & Haq, H. U. (2020) · Multimedia tools and applications · doi:10.1007/s11042-020-09579-x · Cited by 20
“Data augmentation (DA) is a combination of different low-complexity techniques that pervasively used in the literature to minimize the over fitting problems in training a deep neural network [46].”
BackgroundMwaffo, V., Miller, D., & Costello, D. H. (2023) · IEEE Access · doi:10.1109/access.2023.3308822 · Cited by 21
“to significantly enhance detection models [35].”
Deep Learning-Based Gender Classification by Training With Fake Data
Oulad-Kaddour, M., Haddadou, H., Conde, C., Alonso, D. P., Benatchba, K., & Cabello, E. (2023) · IEEE Access · doi:10.1109/access.2023.3328210 · Cited by 22
“In [55], an interesting survey of data augmentation for actual face recognition systems is presented.”
BackgroundPrediction of face age progression with generative adversarial networks
Sharma, N., Sharma, R., & Jindal, N. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11252-w · Cited by 25
“GANs have generated impressive results in many fields [13, 14, 55, 58].”
BackgroundMarmelstein, S., Costa, I. P. D. A., Terra, A. V., da Silva, R. F., Capela, G. P. D. O., Moreira, M. Â. L., Rocha, C. D. S., Gomes, C. F. S., & dos Santos, M. (2024) · Animals · doi:10.3390/ani14050726 · Cited by 16
“In this context, Data Augmentation methods come into play by enriching the dataset with additional information, simulating a more robust environment to test our DEA model, and improving the reliability of the results [48].”
MethodCosenza, B., Picone, A., Volpe, M., & Messineo, A. (2025) · Energy · doi:10.1016/j.energy.2025.137373 · Cited by 18
Image augmentation approaches for small and tiny object detection in aerial images: a review
Nisa, U. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19768-7 · Cited by 24
“Wang et al. [21] overview the categories of transformation that supported the face data augmentation.”
Long, D. T. (2021) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2021.p0953 · Cited by 17
Cyberbully Detection Using BERT with Augmented Texts
Guo, X., Anjum, U., & Zhan, J. (2022) · 2022 IEEE International Conference on Big Data (Big Data) · doi:10.1109/bigdata55660.2022.10020581 · Cited by 12
“Data augmentation has been used in previous literature for image (e.g., face data augmentation in [8]), speech and natural language processing (NLP) [9]–[11] speech and time-series data to reduce overfitting [12], [13].”
MethodZheng, W., Yuan, Q., Zhang, A., Lei, Y., & Pan, G. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126810 · Cited by 15
Optimizing Few-Shot Learning Based on Variational Autoencoders
Wei, R., & Mahmood, A. (2021) · Entropy · doi:10.3390/e23111390 · Cited by 14
“Data augmentation [53,54,56] is a technique used to increase the amount of available training data.”
BackgroundMethodThe Status and Challenges of Image Data Augmentation Algorithms
Wei, J., Wang, Q., Song, X., & Zhao, Z. (2023) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2456/1/012041 · Cited by 11
Detection of Fundamental Quality Traits of Winter Jujube Based on Computer Vision and Deep Learning
Ban, Z., Fang, C., Liu, L., Wu, Z., Chen, C., & Zhu, Y. (2023) · Agronomy · doi:10.3390/agronomy13082095 · Cited by 13
“REVIEW This was an effective way to increase the diversity and number of datasets, thus improving the performance and accuracy of the model [40].”
MethodEnhancement of Track Damage Identification by Data Fusion of Vibration-Based Image Representation
Wang, S., Tang, L., Dou, Y., Li, Z., & Aw, K. C. (2023) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-023-01028-7 · Cited by 11
“CVAE has been demonstrated to be effective in classification tasks in the field of structural health monitoring [18, 19], biomedicine [20, 21], and face recognition [22, 23].”
Boudouh, N., Mokhtari, B., & Foufou, S. (2024) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-024-00345-5 · Cited by 10
“Wong et al. [14] divide classic techniques into two groups.”
Contreras, R. C., Viana, M. S., Bernardino, V. J. S., dos Santos, F. L., Toygar, Ö., & Guido, R. C. (2025) · Scientific Reports · doi:10.1038/s41598-025-97708-7 · Cited by 14
RetractedMiller, D., Mwaffo, V., & Costello, D. H. (2023) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas57906.2023.10156120 · Cited by 12
“Some of these techniques include data augmentation, which is used to add more variability to a small real-world dataset [16]; synthetic data generation, which involves using specialized 3D computer graphics and physics engines to recreate real-world scenarios [17]; and in-house human-assisted…”
BackgroundMethodDisguised heterogeneous face recognition using deep neighborhood difference relational network
Cheema, U., & Moon, S. B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.11.058 · Cited by 9
Solving multiple travelling salesman problem through deep convolutional neural network
Ling, Z., Zhou, Y., & Zhang, Y. (2023) · IET Cyber-Systems and Robotics · doi:10.1049/csy2.12084 · Cited by 8
An Improved Deep Learning Model of Chili Disease Recognition with Small Dataset
Aminuddin, N. F., Tukiran, Z., Joret, A., Tomari, R., & Morsin, M. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130750 · Cited by 9
“Geometric transformation is a data augmentation method that alters the image's geometry by relocating the locations of each pixel's value [16].”
MethodZheng, W., Xia, X., Shi, Y. H., & Men, H. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3304062 · Cited by 8
“This processing method can improve the generalization ability of classifiers and avoid the effects of the overfitting on the results [20], [21].”
MethodAutomated Multi-Class Facial Syndrome Classification Using Transfer Learning Techniques
Sherif, F. F., Tawfik, N., Mousa, D., Abdallah, M. S., & Cho, Y. I. (2024) · Bioengineering · doi:10.3390/bioengineering11080827 · Cited by 17
“[25].”
MethodSarvakar, K., & Rana, K. (2025) · Discover Artificial Intelligence · doi:10.1007/s44163-025-00553-w · Cited by 14
Liu, C., Yi, S., Xie, W., & Bao, X. (2023) · Kybernetes · doi:10.1108/k-06-2023-1107 · Cited by 7
Age and Gender Recognition on Imbalanced Dataset of Face Images with Deep Learning
Yudin, D. A., Shchendrygin, M., & Dolzhenko, A. V. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-50097-9_4 · Cited by 7
An Implicit Identity-Extended Data Augmentation for Low-Resolution Face Representation Learning
Low, C.-Y., & Teoh, A. B. J. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3201374 · Cited by 9
“In a nutshell, the pixel-level identity-invariant transformations, including the advanced GAN-based DA, are inclined to damage the image definitions to some extent [2-3].”
BackgroundSchuerkamp, R., Barrett, J., Bales, A., Wegner, A. L., & Giabbanelli, P. J. (2023) · The Journal of Academic Librarianship · doi:10.1016/j.acalib.2023.102736 · Cited by 7
Object features and face detection performance: Analyses with 3D-rendered synthetic data
Han, J., Karaoğlu, S., Lê, H.-Â., & Gevers, T. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412915 · Cited by 8
“Detailed survey about face specific data augmentation can be found in [21, 22].”
BackgroundYao, Y., Zhang, J., Luo, W., & Dai, Y. (2021) · Processes · doi:10.3390/pr9081266 · Cited by 7
“Another problem is that the traditional DBN is mainly used for face recognition [39], which has the problem of falling into local optimization.”
BackgroundTowards Explainable, Privacy-Preserved Human-Motion Affect Recognition
Malek-Podjaski, M., & Deligianni, F. (2021) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9660129 · Cited by 12
Ahmad, Y., Suciati, N., & Saikhu, A. (2022) · Electrical Power, Electronics, Communications, Controls and Informatics Seminar (EECCIS) · doi:10.1109/eeccis54468.2022.9902911 · Cited by 6
“Transformation in Face Augmentation [27] Generic transformation includes geometric and photometric transformation.”
BackgroundUsgan, M., Ferdiana, R., & Ardiyanto, I. (2021) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1115/1/012009 · Cited by 6
Data Augmentation of Backscatter X-ray Images for Deep Learning-Based Automatic Cargo Inspection
Cho, H.-W., Park, H., Kim, I.-J., & Cho, J. (2021) · Sensors · doi:10.3390/s21217294 · Cited by 6
DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging TasksPreprint
Ding, B., Liu, L., Bing, L., Kruengkrai, C., Nguyen, T. H., Joty, S., Si, L., & Miao, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01549 · Cited by 6
“Data augmentation (Simard et al., 1998) is a useful technique for synthetic data generation, which is widely used in computer vision (Fawzi et al., 2016; D’Innocente et al., 2017; Wang et al., 2019) and speech (Schl¨uter and Grill, 2015; Ko et al., 2017).”
MethodYang, Z., Wang, Y., Shi, H., & Qiu, Q. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8110151 · Cited by 10
Data Augmentation Using Convolutional Autoencoder for Facial Emotion Recognition
Kwon, B. (2025) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic64972.2025.10879763 · Cited by 5
Semi-Supervised Cross-Spectral Face Recognition with Small Datasets
Nanduri, A., & Chellappa, R. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00069 · Cited by 6
“A natural way to deal with the lack of labeled data is data generation and data augmentation [5,28, 38].”
BackgroundA novel data augmentation approach for ego-lane detection enhancement
Yousri, R., Moussa, K., Elattar, M., Madian, A. H., & Darweesh, M. S. (2023) · Evolving Systems · doi:10.1007/s12530-023-09533-w · Cited by 6
“We can mimic various images taken at different angles and positions for the same scene using PT from just one image (Wang et al. 2020).”
InfluentialModel for Determining the Psycho-Emotional State of a Person Based on Multimodal Data Analysis
Shakhovska, N., Zherebetskyi, O., & Lupenko, S. A. (2024) · Applied Sciences · doi:10.3390/app14051920 · Cited by 4
FSErasing: Improving Face Recognition with Data Augmentation Using Face Parsing
Kawai, H., Ito, K., Chen, H.-T., & Aoki, T. (2024) · IET Biometrics · doi:10.1049/2024/6663315 · Cited by 4
Pan, Y., Jiang, H., Li, F., Wang, F., Lv, C., Wang, Y., Jia, X., Shang, X., & Zhou, H. (2025) · Infrared Physics & Technology · doi:10.1016/j.infrared.2025.105932 · Cited by 4
A Prototypical Network Approach for Evaluating Generated Emotional Speech
Baird, A., Mertes, S., Milling, M., Stappen, L., Wiest, T., André, E., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1123 · Cited by 5
“When augmenting a training set, considering the quality and diversity of the new data to the already known data is a necessary factor [28].”
BackgroundML-Stealer: Stealing Prediction Functionality of Machine Learning Models with Mere Black-Box Access
Liu, G., Wang, S., Wan, B., Wang, Z., & Wang, C. (2021) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom53373.2021.00083 · Cited by 4
On the pitfalls of learning with limited data: A facial expression recognition case study
Santander, M. R., Albarracín, J. F. H., & Rivera, A. R. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114991 · Cited by 5
Han, F., Liang, Y., Ling, Q.-H., & Han, H. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3560097 · Cited by 5
“Tosolvethisproblem,numerousmethodsofdataaugmenta-tionhavebeenproposed[3],[4].”
Anomaly-Focused Augmentation Method for Industrial Visual Inspection
de León, M. A. L., Hameed, I. A., & Koziorek, J. (2025) · IEEE Access · doi:10.1109/access.2025.3570075 · Cited by 7
“Computer vision engineers typically enforce strict control over input variables such as lighting conditions, object positioning, and other environmental factors to ensure consistency [3].”
LATS: Low resource abstractive text summarization
van Yperen, C., Frăsincar, F., & Kanfoudi, K. E. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128078 · Cited by 3
LAMBO: Landmarks Augmentation With Manifold-Barycentric Oversampling
Bespalov, I. R., Buzun, N., Kachan, O., & Dylov, D. V. (2022) · IEEE Access · doi:10.1109/access.2022.3219934 · Cited by 7
“For faces, the survey [59] covers a large set of augmentation methods, ranging from attribute transformations [36] to generative methods ( e.g. , GAN-based [47,66]).”
Facial Expression Recognition Using 3D Points Aware Deep Neural Network
Trimech, I. H., Maalej, A., & Amara, N. E. B. (2021) · Traitement du signal · doi:10.18280/ts.380209 · Cited by 3
“We have reported an encouraging average recognition rate of 97.23% overcoming most of state-of-art works [30, 32-34].”
BackgroundInfluentialA Fair Generative Model Using LeCam Divergence
Um, S., & Suh, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26196 · Cited by 4
“…et al. 2014; Karras, Laine, and Aila 2019) have played a crucial role to enrich training data for a widening array of applications such as face recognition, natural language processing, and medical imaging (Wang, Wang, and Lian 2019; Chang, Chuang, and Lee 2018; Yi, Walia, and Babyn 2019).”
BackgroundZhang, J., Wang, W., & Che, Q. (2024) · Electronics · doi:10.3390/electronics13152941 · Cited by 3
Atenco-Vázquez, J. C., Moreno-Rodríguez, J. C., & Ramirez, J. (2023) · Algorithms · doi:10.3390/a16020066 · Cited by 5
“Wang et al. [20,55] describe different types of image transformations for data augmentation to train deep learning models for face recognition.”
BackgroundMethods for deep learning model failure detection and model adaption: A survey
Wu, X., Hu, Z., Pei, K., Song, L., Cao, Z. W., & Zhang, S. (2021) · IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW) · doi:10.1109/issrew53611.2021.00066 · Cited by 3
Generating and Improving a Dataset of Masked Faces Using Data Augmentation
Ayad, W., Mahdi, S. Q., & Al‐Naji, A. (2023) · Journal of Techniques · doi:10.51173/jt.v5i2.1140 · Cited by 4
“Data augmentation can increase facial recognition systems’ accuracy by training them on the original data set images and the images that were modified using data augmentation techniques [24,25].”
BackgroundClass preserving projections and data augmentation for appearance-based face recognition
Soldera, J., & Scharcanski, J. (2024) · Pattern Analysis and Applications · doi:10.1007/s10044-024-01388-4 · Cited by 2
Bartuzi-Trokielewicz, E., Martinek, A., & Kordas, A. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00182 · Cited by 2
“The survey [36] extensively reviews existing techniques for face data augmentation, categorizing them into distinct transformation types and methods to improve model robustness under diverse real-world conditions.”
Metadata
- Authors
- Wang, X., Wang, K., & Lian, S.
- Affiliations
- China United Network Communications Group (China) (CN)
- Corresponding author
- Wang, Xiang
- ORCID
- Wang, Xiang
- Venue
- Neural Computing and Applications
- Published
- 2020-03-17
- Volume
- 32
- Issue
- 19
- Pages
- 15503-15531
- ISSN
- 0941-0643 (ISSN-L)
- 1433-3058
- OpenAlex
- W2942077508
- Cited by
- 141
- References
- 104
- Citations by year
- 2026: 9 · 2025: 13 · 2024: 26 · 2023: 31 · 2022: 20 · 2021: 28 · 2020: 12
- FWCI
- 8.84
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Neural Computing and Applications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
- 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 and Expression Recognition
- Keywords
- generative adversarial networks, deep neural network, training data quality
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.