Augmentation of small training data using GANs for enhancing the performance of image classification
Abstract
It is difficult to achieve high performance without sufficient training data for deep convolutional neural networks (DCNNs) to learn. Data augmentation plays an important role in improving robustness and preventing overfitting in machine learning for many applications such as image classification. In this paper, a novel method for data augmentation is proposed to solve the problem of machine learning with small training datasets. The proposed method can synthesise similar images with rich diversity from only a single original training sample to increase the number of training data by using generative adversarial networks (GANs). It is expected that the synthesised images possess class-informative features, which may be in the validation or testing data but not in the training data due to that the training dataset is small, and thus they can be effective as augmented training data to improve the classification accuracy of DCNNs. The experimental results have demonstrated that the proposed method with a novel GAN framework for image training data augmentation can significantly enhance the classification performance of DCNNs for applications where original training data is limited.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Generative adversarial networks have become popular for generating EEG signals in recent years.
“Generative adversarial networks have become popular for generating EEG signals in recent years (Hung and Gan, 2021)”
From Data Augmentation for Deep Neural Networks Model in EEG Classification Task: A Review (2021) · cites this paper as Hung and Gan, 2021
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · see citing works
(2014) · Cited by 33,419 · see citing works
Batch 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 · see citing works
Labaca-Castro, R. (2023) · Springer eBooks · doi:10.1007/978-3-658-40442-0_9 · Cited by 21,100 · see citing works
GAN（Generative Adversarial Nets）
淳司, 柴. (2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,268 · see citing works
Unsupervised 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 · see citing works
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365 · see citing works
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · see citing works
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition
Arandjelović, R., Gronát, P., Torii, A., Pajdla, T., & Šivic, J. (2016) · 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/cvpr.2016.572 · Cited by 3,441 · see citing works
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · see citing works
Conditional Image Synthesis With Auxiliary Classifier GANsPreprint
Odena, A., Olah, C., & Shlens, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09585 · Cited by 2,968 · see citing works
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Perez, L., & Wang, J. (2017) · arXiv · doi:10.48550/arxiv.1712.04621 · Cited by 2,499 · see citing works
NetVLAD: CNN architecture for weakly supervised place recognitionPreprint
Arandjelović, R., Gronát, P., Torii, A., Pajdla, T., & Šivic, J. (2015) · arXiv (Cornell University) · Cited by 1,790 · see citing works
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
Stallkamp, J., Schlipsing, M., Salmen, J., & Igel, C. (2011) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2011.6033395 · Cited by 1,190 · see citing works
Are GANs Created Equal? A Large-Scale StudyPreprint
Lučić, M., Kurach, K., Michalski, M., Gelly, S., & Bousquet, O. (2017) · Neural Information Processing Systems · doi:10.48550/arxiv.1711.10337 · Cited by 1,175 · see citing works
Pros and cons of GAN evaluation measures
Borji, A. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2018.10.009 · Cited by 963 · see citing works
Synthetic data augmentation using GAN for improved liver lesion classification
Frid-Adar, M., Klang, E., Amitai, M. M., Goldberger, J., & Greenspan, H. K. (2018) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi.2018.8363576 · Cited by 919 · see citing works
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational LearningPreprint
Srivastava, A., Valkov, L., Russell, C., Gutmann, M. U., & Sutton, C. A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.07761 · Cited by 524 · see citing works
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Bynagari, N. B. (2019) · Asian Journal of Applied Science and Engineering · doi:10.18034/ajase.v8i1.9 · Cited by 514 · see citing works
Fujisawa, Y., Otomo, Y., Ogata, Y., Nakamura, Y., Fujita, R., Ishitsuka, Y., Watanabe, R., Okiyama, N., Ohara, K., & Fujimoto, M. (2018) · British Journal of Dermatology · doi:10.1111/bjd.16924 · Cited by 316 · see citing works
Data Augmentation for Low-Resource Neural Machine Translation
Fadaee, M., Bisazza, A., & Monz, C. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p17-2090 · Cited by 266 · see citing works
Data-augmentation for reducing dataset bias in person re-identification
McLaughlin, N., del Rincón, J. M., & Miller, P. C. (2015) · IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) · doi:10.1109/avss.2015.7301739 · Cited by 93 · see citing works
Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data AugmentationPreprint
Hauberg, S., Freifeld, O., Larsen, A., Fisher, J. S., & Hansen, L. K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.02795 · Cited by 78 · see citing works
Mayya, V., Pai, R. M., & Pai, M. M. M. (2016) · International Conference on Advances in Computing, Communications and Informatics (ICACCI) · doi:10.1109/icacci.2016.7732128 · Cited by 49 · see citing works
Flagged first, then by citations
3 of the 30 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Data Augmentation for Deep Neural Networks Model in EEG Classification Task: A Review
He, C., Liu, J., Zhu, Y., & Du, W. (2021) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2021.765525 · Cited by 105 · see citing works
“Generative adversarial networks have become popular for generating EEG signals in recent years (Hung and Gan, 2021), although it has still not been clearly demonstrated to be the most effective strategy across different EEG tasks.”
BackgroundPacheco, F. A. L., Hermosilla, G., Bustamante, O. P., Villavicencio, G. E., Allende‐Cid, H., Palma, J., Valenzuela, P., García, J., Carpanetti, A., Minatogawa, V., et al. (2022) · Mathematics · doi:10.3390/math10234396 · Cited by 23 · see citing works
Transfer-GAN: data augmentation using a fine-tuned GAN for sperm morphology classification
Abbasi, A., Bahrami, S., Hemmati, T., & Mirroshandel, S. A. (2023) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2023.2238846 · Cited by 5 · see citing works
Transformer-based GAN-augmented Defender for Adversarial USB Keystroke Injection Attacks
Chillara, A. K., Saxena, P., & Maiti, R. R. (2025) · International Conference on Distributed Computing and Networking (ICDCN) · doi:10.1145/3700838.3700871 · Cited by 5 · see citing works
Low-shot Image Classification Using Mixture of Experts
Zhang, Z., & Sathe, S. K. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888050 · Cited by 2 · see citing works
AI and ML in Understanding Biosphere and Cross-Sphere Interactions
Patra, P. P., & Behera, S. (2026) · Earth and environmental sciences library · doi:10.1007/978-3-032-11426-6_14 · Cited by 1 · see citing works
Detection of Pathological Myopia from Fundus Images
Ali, S., & Raut, S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-2100-3_17 · Cited by 1 · see citing works
Automatic Detection of Pathological Myopia Using Smartphone App
Ali, S., & Raut, S. (2022) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci58124.2022.00078 · Cited by 1 · see citing works
Data Augmentation Method Using Generative Model for Skeleton-based Human Action Recognition
Hamabe, S., & Yamada, K. (2024) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.144.1209
Structurally Regularised Probabilistic Representation for Long-Tailed Medical Image Recognition
Tao, Y., Xiao, R., Li, Z., Yang, C., Zhang, Q., Yuan, X., & Fu, G. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00069
- Authors
- Hung, S.-K., & Gan, J. Q.
- Affiliations
- University of Essex (GB)
- ORCID
- Gan, John Q.
- Venue
- 2020 25th International Conference on Pattern Recognition (ICPR)
- Publisher
- IEEE
- Published
- 2021-01-10
- Pages
- 3350-3356
- ISSN
- 1041-3278 (ISSN-L)
- OpenAlex
- W3159732019
- Cited by
- 10
- References
- 30
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 1 · 2023: 2 · 2022: 2 · 2021: 1
- FWCI
- 0.49
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition (publishedVersion)
- 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 › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- data augmentation, generative adversarial networks, image classification, limited training data, synthetic image generation, deep convolutional neural networks, overfitting
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
