The DOI matches its Crossref record; 113 of the 113 references it cites were found in a registry or an index.
A survey on face data augmentation for the training of deep neural networks
Open accessAbstract
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: 51
- 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
- Cubuk E.D, Zoph B, Mane D, Vasudevan V, Le QV (2019) Autoaugment: Learning augmentation strategies from data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 113–123
- 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
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: A survey on face data augmentation for the training of deep neural networks. https://app.cochat.ai/papers/10.1007/s00521-020-04748-3
- The paper
- Wang, X., Wang, K., & Lian, S. (2020). A survey on face data augmentation for the training of deep neural networks. Neural Computing and Applications. https://doi.org/10.1007/s00521-020-04748-3
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.