Albumentations: Fast and Flexible Image Augmentations
Open accessThe DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.
Abstract
Data augmentation is a commonly used technique for increasing both the size and the diversity of labeled training sets by leveraging input transformations that preserve corresponding output labels. In computer vision, image augmentations have become a common implicit regularization technique to combat overfitting in deep learning models and are ubiquitously used to improve performance. While most deep learning frameworks implement basic image transformations, the list is typically limited to some variations of flipping, rotating, scaling, and cropping. Moreover, image processing speed varies in existing image augmentation libraries. We present Albumentations, a fast and flexible open source library for image augmentation with many various image transform operations available that is also an easy-to-use wrapper around other augmentation libraries. We discuss the design principles that drove the implementation of Albumentations and give an overview of the key features and distinct capabilities. Finally, we provide examples of image augmentations for different computer vision tasks and demonstrate that Albumentations is faster than other commonly used image augmentation tools on most image transform operations.
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?
In the citing paper
“The data set used to build the diagnostic model is the ISBI 2019 data set [16–20], and 10661 cell pictures of 73 subjects were selected, including 7272 pictures of leukemic B-lymphoblast cells (cancer cells) from 47 all patients and 3389 pictures of B-lymphoid precursors (normal cells) from 26 healthy persons.”
From Method for diagnosis of acute lymphoblastic leukemia based on vit-cnn ensemble model (2021) · cites this paper as [20]
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
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 · cited 1×
“In computer vision, ImageNet database and the Large Scale Visual Recognition Challenge [23] have become the main platforms for benchmarking modern deep learning models for image classification after the breakthrough performance of AlexNet in 2012 that nearly halved previous state-of-the-art error rates [24].”
MethodU-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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“In computer vision, ImageNet database and the Large Scale Visual Recognition Challenge [23] have become the main platforms for benchmarking modern deep learning models for image classification after the breakthrough performance of AlexNet in 2012 that nearly halved previous state-of-the-art error rates [24].”
MethodGradient-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 · cited 1×
“Basic image augmentations have been identified as an essential technique for training neural networks for visual recognition before that [25], and AlexNet extended their use to random crops, translations, horizontal flips, and altering the intensities of RGB channels to achieve that seminal result.”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 2×
“Albumentations supports seamless augmentation of bounding boxes in three most common formats: COCO [59], PascalVOC [60], and YOLO [61].”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 5×
“To support users of different deep learning frameworks, Albumentations provides a convenient Python interface to enable a seamless integration with PyTorch [13], Keras [12], and Tensorflow [11].”
BackgroundMethodInfluentialA survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332 · cited 1×
“One typical use case for keypoint annotations is image registration, a common task in biomedical image analysis [29,63].”
Background
Research works printed but not linked: 5
- Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (May, January 30). mixup: Beyond empirical risk minimization. Proceedings of the International Conference on Learning Representations (ICLR), Vancouver, BC, Canada.
- Lee, H., Hwang, S.J., and Shin, J. (2019). Rethinking Data Augmentation: Self-Supervision and Self-Distillation. arXiv.
- Lim, S., Kim, I., Kim, T., Kim, C., and Kim, S. (2019, January 8–14). Fast AutoAugment. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada.
- Brito, J.J., Li, J., Moore, J.H., Greene, C.S., Nogoy, N.A., Garmire, L.X., and Mangul, S. (2020). Enhancing rigor and reproducibility by improving software availability, usability, and archival stability. arXiv.
- Rakhlin, A., Tiulpin, A., Shvets, A.A., Kalinin, A.A., Iglovikov, V.I., and Nikolenko, S. (2019, January 16–20). Breast tumor cellularity assessment using deep neural networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops, Long Beach, CA, USA. · doi:10.1101/628693
Cited by
Items 401–500 of 1,006
Ceramic tableware surface defect detection based on deep learning
Sun, P., Hua, C., Ding, W., Hua, C., Liu, P., & Lei, Z. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109723 · Cited by 27
Paddy-YOLO: An accurate method for rice pest detection
Zheng, Y., Zheng, W., & Du, X. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110777 · Cited by 28
Improving Semi-Supervised Learning for Audio Classification with FixMatch
Grollmisch, S., & Cano, E. (2021) · Electronics · doi:10.3390/electronics10151807 · Cited by 32
Baltruschat, I. M., Ćwieka, H., Krüger, D., Zeller‐Plumhoff, B., Schlünzen, F., Willumeit‐Römer, R., Moosmann, J. P., & Heuser, P. (2021) · Scientific Reports · doi:10.1038/s41598-021-03542-y · Cited by 28
Choudhary, A. K., Jansche, A., Grubesa, T., Trier, F., Goll, D., Bernthaler, T., & Schneider, G. (2022) · Materials Characterization · doi:10.1016/j.matchar.2022.111790 · Cited by 27
Xie, J., Pu, X., He, J., Qiu, Y., Lu, C. Y., Gao, W., Wang, X., Lu, H., Shi, J., Xu, Y., et al. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105520 · Cited by 28
Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets
Voo, K. T. R., Jiang, L., & Loy, C. C. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00517 · Cited by 39
Structure-Oriented Transformer for retinal diseases grading from OCT images
Shen, J., Hu, Y., Zhang, X., Gong, Y., Kawasaki, R., & Liu, J. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106445 · Cited by 35
LRDNet: Lightweight LiDAR Aided Cascaded Feature Pools for Free Road Space Detection
Khan, A. A., Shao, J., Rao, Y., She, L., & Shen, H. T. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3230330 · Cited by 30
“The second level of random augmentations was introduced during the training process by using [38].”
Stoimchev, M., Kocev, D., & Džeroski, S. (2023) · Remote Sensing · doi:10.3390/rs15020538 · Cited by 29
Ren, Z., Wang, L., & He, Z. (2023) · Remote Sensing · doi:10.3390/rs15153829 · Cited by 31
Katsampiris-Salgado, K., Dimitropoulos, N., Gkrizis, C., Michalos, G., & Makris, S. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.05.015 · Cited by 31
Forensic Analysis of Synthetically Generated Western Blot Images
Mandelli, S., Cozzolino, D., Cannas, E. D., Cardenuto, J. P., Moreira, D., Bestagini, P., Scheirer, W. J., Rocha, A., Verdoliva, L., Tubaro, S., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3179116 · Cited by 26
“For instance, co-occurrences have been used for spotting subtle differences (usually not visible at human inspection) in the textural features of real versus manipulated natural images (through splicing) [32] and of real versus synthetic natural images [33], [34].”
BackgroundMethodBarrientos-Espillco, F., Gascó, E., López-González, C. I., Gómez-Silva, M. J., & Pajares, G. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110315 · Cited by 26
Alkhaldi, N. A., & Alabdulathim, R. E. (2024) · Applied Sciences · doi:10.3390/app14177795 · Cited by 26
A Deep Learning Approach to Hazard Detection for Autonomous Lunar Landing
Moghe, R., & Zanetti, R. (2020) · The Journal of the Astronautical Sciences · doi:10.1007/s40295-020-00239-8 · Cited by 27
“Additionally, a popular technique called data augmentation is used to add diversity to the training data [7].”
MethodDeep Learning based Crop Row Detection with Online Domain Adaptation
Doha, R. M., Hasan, M. A., Anwar, S., & Rajendran, V. P. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467155 · Cited by 29
Deep learning-based classification of DSA image sequences of patients with acute ischemic stroke
Mittmann, B. J., Braun, M., Runck, F., Schmitz, B., Tran, T. N., Yamlahi, A., Maier‐Hein, L., & Franz, A. M. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02654-8 · Cited by 28
“Data augmentation was dynamically performed during training based on the Albumentations library [4].”
MethodSelf-Supervised Learning for Annotation Efficient Biomedical Image Segmentation
Rettenberger, L., Schilling, M. P., Elser, S., Böhland, M., & Reischl, M. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3252889 · Cited by 30
“The Albumentations [5] library is used to implement the image augmentations.”
Toward Robust Facial Action Units’ Detection
Yang, J., Hristov, Y., Shen, J., Lin, Y., & Pantić, M. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3257542 · Cited by 29
“The content augmentations are implemented with public library albumentations [8], including Gaussian blur, ImageCompression, and CoarseDropout.”
MethodWeakly-Supervised Crack Detection
Inoue, Y., & Nagayoshi, H. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3286934 · Cited by 28
“Elastic Transform implementation in Albumenta-tions [22] has three parameters: α , σ , alpha_affine. σ is fixed at 12 to prevent excessive deformation, and alpha_affine is fixed at 0.2.”
InfluentialEnhancing EfficientNet-YOLOv4 for Integrated Circuit Detection on Printed Circuit Board (PCB)
Tay, S. C., Wahab, M. N. A., Mohamed, A. S. A., Noor, M. H. M., Kang, K. B., Chuan, L. L., & Liau, W. J. B. (2024) · IEEE Access · doi:10.1109/access.2024.3359639 · Cited by 31
“Albumentations [40], an open-source Python library compatible with popular deep learning frameworks such as TensorFlow and PyTorch, was utilized for offline image augmentation.”
MethodSAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model OCTA Image Segmentation Tasks
Wang, C., Chen, X., Ning, H., & Li, S. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446904 · Cited by 26
“The adopted data augmentation tool is Albumentations [19].”
MethodCormier, M., Schmid, Y., & Beyerer, J. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00038 · Cited by 34
“Its principle is based on the popular image augmentation library Albumentations [2].”
BackgroundHasan, M. J., Mazumdar, S., & Momen, S. (2025) · IEEE Access · doi:10.1109/access.2025.3595390 · Cited by 23
Liu, Q., Kampffmeyer, M., Jenssen, R., & Salberg, A.-B. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2098078 · Cited by 28
“The albumentations library (Buslaev et al. 2020) for data augmentation is utilized in this work.”
MethodZhang, Z., Zhong, S.-H., Fares, A. H., & Liu, Y. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103416 · Cited by 25
Data Augmentation for Building Footprint Segmentation in SAR Images: An Empirical Study
Wangiyana, S., Samczyński, P., & Gromek, A. (2022) · Remote Sensing · doi:10.3390/rs14092012 · Cited by 25
Multi-Axis 3D Printing Defect Detecting by Machine Vision with Convolutional Neural Networks
Zhang, H., Zong, Z., Yao, Y., Hu, Q., Aburaia, M., & Lammer, H. (2022) · Experimental Techniques · doi:10.1007/s40799-022-00577-2 · Cited by 26
“Therefore, to further increase the size of the training dataset and enhance the generalizability of the CNN model, data augmentation can increase the diversity of training samples in the case of limited data, improving the model’s robustness avoid over-fitting [23].”
BackgroundSeker, A. C., & Ahn, S. C. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117310 · Cited by 25
Semi-supervised domain adaptation for segmentation models on different monitoring settings
Hong, Y., Chern, W., Nguyen, T., Cai, H., & Kim, H. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104773 · Cited by 29
Classification of cassava leaves (Manihot esculenta) using transfer learning
Pratondo, A. (2023) · Indonesian Journal of Electrical Engineering and Informatics (IJEEI) · doi:10.52549/ijeei.v11i2.4685 · Cited by 27
Filia, B. J., Lienardy, F. F., Laksana, I. K. P. B., Jordan, J. A., Siento, J. G., Honova, S. M., Hasana, S., & Parmonangan, I. H. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.10.552 · Cited by 25
Boiko, D. A., Pentsak, E. O., Cherepanova, V. A., Gordeev, E. G., & Ananikov, V. P. (2021) · Chemical Science · doi:10.1039/d0sc05696k · Cited by 25
Najafian, K., Ghanbari, A., Stavness, I., Jin, L., Shirdel, G. H., & Maleki, F. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00155 · Cited by 31
“All augmentations were conducted using the Albumentation package version 0.5.2 [3].”
MethodInfluentialObject-Based Augmentation for Building Semantic Segmentation: Ventura and Santa Rosa Case Study
Illarionova, S., Nesteruk, S., Shadrin, D., Ignatiev, V., Pukalchik, M., & Oseledets, I. V. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00191 · Cited by 26
“Augmentation means applying transformations (such as flip, rotate, scale, change brightness and contrast) to the original images to increase useful samples that allow training more robust algorithms [4].”
MethodTang, P., Yan, X., Yang, N., Hu, X., Menze, B. H., Krammer, S., & Lasser, T. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110604 · Cited by 36
Zhang, S., & Ma, J. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114349 · Cited by 26
Automated Lung and Colon Cancer Classification Using Histopathological Images
Ji, J., Zhang, W., 耿义群, Wang, H., Wang, C., Dong, Y., Lin, R., Chen, Z., Huang, J., Hong, L., et al. (2024) · Biomedical Engineering and Computational Biology · doi:10.1177/11795972241271569 · Cited by 32
Fire and Smoke Detection Based on Improved YOLOV11
Xue, Z., Kong, L., Wu, H., & Chen, J. (2025) · IEEE Access · doi:10.1109/access.2025.3564434 · Cited by 28
Autonomous Coordinated Control of the Light Guide for Positioning in Vitreoretinal Surgery
Koyama, Y., Marinho, M. M., Mitsuishi, M., & Harada, K. (2022) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2022.3147033 · Cited by 28
“Furthermore, we used common augmentation strategies [48]: blur, additive noise, image compression, rotation, optical distortion, and random brightness, and contrast.”
MethodTime-Series Growth Prediction Model Based on U-Net and Machine Learning in Arabidopsis
Chang, S., Lee, U., Hong, M. J., Jo, Y. D., & Kim, J. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.721512 · Cited by 28
Baur, D., Bieck, R., Berger, J., Neumann, J., Henkelmann, J., Neumuth, T., Heyde, C., & Voelker, A. (2021) · European Spine Journal · doi:10.1007/s00586-021-07073-y · Cited by 24
Plant disease symptom segmentation in chlorophyll fluorescence imaging with a synthetic dataset
Sapoukhina, N., Boureau, T., & Rousseau, D. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2022.969205 · Cited by 25
“For this data augmentation, we used Albumentations library (Buslaev et al., 2020).”
MethodDP-ViT: A Dual-Path Vision Transformer for Real-Time Sonar Target Detection
Sun, Y., Zheng, H., Zhang, G., Ren, J., Xu, H., & Xu, C. (2022) · Remote Sensing · doi:10.3390/rs14225807 · Cited by 26
AutoOLA: Automatic object level augmentation for wheat spikes counting
Zaji, A., Liu, Z., Xiao, G. G., Bhowmik, P., Sangha, J. S., & Ruan, Y. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107623 · Cited by 24
Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications
Stacke, K., Unger, J., Lundström, C. F., & Eilertsen, G. (2022) · The Journal of Machine Learning for Biomedical Imaging · doi:10.59275/j.melba.2022-f9a1 · Cited by 34
Learning Adaptive Dense Event Stereo from the Image Domain
Cho, H., Cho, J., & Yoon, K. (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/cvpr52729.2023.01707 · Cited by 30
“3, we utilize the Blur and OpticalDistortion transforms from library [4].”
MethodSafdar, M., Paul, P. P., Lamouche, G., Wood, G., Zimmermann, M., Hannesen, F., Bescond, C., Wanjara, P., & Zhao, Y. F. (2023) · Computers in Industry · doi:10.1016/j.compind.2023.104037 · Cited by 26
Scalable Industrial Visual Anomaly Detection With Partial Semantics Aggregation Vision Transformer
Yao, H., Luo, W., Lou, J., Yu, W., Zhang, X., Qiang, Z., & Shi, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3343832 · Cited by 31
“Specifically, we applied random data augmentation techniques using the Albumentations library [43] to process image samples.”
MethodKarn, P. K., & Abdulla, W. H. (2024) · Bioengineering · doi:10.3390/bioengineering11030240 · Cited by 24
“Applying the Albumentations 1.4 Python library [40], the study incorporates nine diverse augmentation techniques: vertical flip, horizontal flip, random snow, CLAHE, blur, invert image, coarse dropout, downscale, and equalise.”
MethodInfluentialIntelligent deep learning supports biomedical image detection and classification of oral cancer
Chen, R., Wang, Q., & Huang, X. (2024) · Technology and Health Care · doi:10.3233/thc-248041 · Cited by 26
“Albumentations [16] is a powerful data enhancement tool that contains rich data enhancement methods, such as image resizing, scaling, rotation, flipping, etc.”
BackgroundJoshi, D., Mishra, V., Srivastav, H., & Goel, D. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10521-x · Cited by 25
PathML: A unified framework for whole-slide image analysis with deep learningPreprint
Berman, A. G., Orchard, W. R., Gehrung, M., & Markowetz, F. M. (2021) · medRxiv · doi:10.1101/2021.07.07.21260138 · Cited by 31
DFGC 2021: A DeepFake Game Competition
Peng, B., Fan, H., Wang, W., Dong, J., Li, Y., Lyu, S., Li, Q., Sun, Z., Chen, H., Chen, B., et al. (2021) · 2021 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb52358.2021.9484387 · Cited by 23
“We first train a detector D using the CelebDF dataset and the fake images generated by Faceshifter, where the backbone network is EfficientNet-B7.”
MethodInfluentialDeep-Learning-Based Defect Detection for Light Aircraft With Unmanned Aircraft Systems
Connolly, L., Garland, J. W., O’Gorman, D., & Tobin, E. F. (2024) · Machine Learning with Applications · doi:10.1109/access.2024.3412204 · Cited by 23
Volpato, L., Wright, E. M., & Gomez, F. E. (2024) · Plant Phenomics · doi:10.34133/plantphenomics.0278 · Cited by 25
“Additionally, the “Albumentations ” Python library [ 62 ] was also implemented using “OneOf” method to perform a robust image augmentation to increase the quality of trained models.”
InfluentialRaha, A. D., Kim, K. T., Adhikary, A., Gain, M., Han, Z., & Hong, C. S. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3573711 · Cited by 36
Nesteruk, S., Illarionova, S., Akhtyamov, T., Shadrin, D., Somov, A., Pukalchik, M., & Oseledets, I. V. (2022) · IEEE Access · doi:10.1109/access.2022.3154709 · Cited by 23
“One of the first definitions of image augmentation may be stated as is a technique that applies various transformations to original images to increase training data variability [51].”
BackgroundContrastive learning with text augmentation for text classification
Jia, O., Huang, H., Ren, J., Xie, L., & Xiao, Y. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04453-3 · Cited by 23
“Data augmentation strategies for improving the performance of classification models have been broadly studied in deep learning [11, 12, 18].”
BackgroundMethodChen, W., Mei, Z.-G., Ward, L. T., Monsen, B., Wen, J., Zaluzec, N. J., Yacout, A. M., & Li, M. (2023) · Acta Materialia · doi:10.1016/j.actamat.2023.119013 · Cited by 23
Robust Automatic Motorcycle Helmet Violation Detection for an Intelligent Transportation System
Tran, D. N., Pham, L. H., Jeon, H., Nguyen, H.-H., Jeon, H.-M., Tran, T. H.-P., & Jeon, J. W. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00563 · Cited by 23
“To enhance the model’s accuracy and mitigate overfitting, we have employed a dataset augmentation strategy [2] (as shown in Figure 4).”
MethodBavirisetti, D. P., Martinsen, H. R., Kiss, G. H., & Lindseth, F. (2023) · IEEE Open Journal of Intelligent Transportation Systems · doi:10.1109/ojits.2023.3335648 · Cited by 29
Yaras, C. B., Kassaw, K., Huang, B., Bradbury, K., & Malof, J. M. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3340412 · Cited by 29
Improved YOLOv5 Based Deep Learning System for Jellyfish Detection
Pham, T.-N., Nguyen, V.-H., Kwon, K., Kim, J., & Huh, J. (2024) · IEEE Access · doi:10.1109/access.2024.3405452 · Cited by 23
“Thus, apart from YOLOv5 default hyperparameters data augmentation like a mosaic, copy_paste, we apply some image processing techniques (i.e, motion blur, random brightness contrast, CLAHE, To Gray) while training YOLOv5 model using albumentation library [46] as can be seen in Fig.”
MethodWheat Powdery Mildew Detection with YOLOv8 Object Detection Model
Önler, E., & Köycü, N. D. (2024) · Applied Sciences · doi:10.3390/app14167073 · Cited by 24
Gessain, G., Anzali, A.-A., Lerousseau, M., Mulder, K., Bied, M., Auperin, A., Stockholm, D., Signolle, N., Sassi, F., Costa, M. E. M. D., et al. (2024) · Cancer Discovery · doi:10.1158/2159-8290.cd-24-0018 · Cited by 34
Park, G.-T., & Lee, Y. (2024) · Fire · doi:10.3390/fire7100369 · Cited by 28
Sapoukhina, N., Samiei, S., Rasti, P., & Rousseau, D. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00312 · Cited by 25
“For this data augmentation we used Albumentations library [5].”
MethodAGUnet: Annotation-guided U-net for fast one-shot video object segmentation
Yin, Y., Xu, D., Wang, X., & Zhang, L. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107580 · Cited by 28
Humblot-Renaux, G., Marchegiani, L., Moeslund, T. B., & Gade, R. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3144491 · Cited by 29
Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised LearningPreprint
Paul, S., & Ganju, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.08369 · Cited by 43
“For data augmentation, we use the albumentations package [6]. segmentation_models_pytorch ( smp for short) package [40] is used for developing the segmentation models.”
MaS-TransUNet: A Multiattention Swin Transformer U-Net for Medical Image Segmentation
Upadhyay, A. K., & Bhandari, A. K. (2024) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2024.3477528 · Cited by 29
“We employed the open-source Python library “Albumentations” [45] to implement a wide range of image augmentation techniques.”
Andriyanov, N. A. (2021) · Applied Sciences · doi:10.3390/app11115235 · Cited by 22
Bloch, L., Brüngel, R., & Friedrich, C. M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-94907-5_3 · Cited by 28
“Two augmentation pipelines – one baseline pipeline and one extended pipeline – were implemented using the Albumentations [2] package.”
MethodSpatial-Net for Human-Object Interaction Detection
Mansour, A. E., Mohammed, A., Elsayed, H. A. E. A., & Elramly, S. (2022) · IEEE Access · doi:10.1109/access.2022.3199380 · Cited by 22
“We employ data augmentation using Albumentations [59] (random flip and random rotate) and we use the Adam optimizer [60] for loss function optimization during training.”
MethodInterpretable Deep Learning Applied to Rip Current Detection and Localization
Rampal, N., Shand, T. D., Wooler, A., & Rautenbach, C. (2022) · Remote Sensing · doi:10.3390/rs14236048 · Cited by 22
“Not addressed in this work.”
Semi-Self-Supervised Learning for Semantic Segmentation in Images with Dense Patterns
Najafian, K., Ghanbari, A., Kish, M. S., Eramian, M., Shirdel, G. H., Stavness, I., Jin, L., & Maleki, F. (2023) · Plant Phenomics · doi:10.34133/plantphenomics.0025 · Cited by 24
BEST: Building evidences from scattered templates for accurate contactless palmprint recognition
Yulin, F., & Kumar, A. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109422 · Cited by 26
PickYOLO: Fast deep learning particle detector for annotation of cryo electron tomograms
Genthe, E., Miletic, S., Tekkali, I., James, R. H., Marlovits, T. C., & Heuser, P. (2023) · Journal of Structural Biology · doi:10.1016/j.jsb.2023.107990 · Cited by 22
Lami, K., Ota, N., Yamaoka, S., Bychkov, A., Matsumoto, K., Uegami, W., Munkhdelger, J., Seki, K., Sukhbaatar, O., Attanoos, R. L., et al. (2023) · American Journal Of Pathology · doi:10.1016/j.ajpath.2023.07.002 · Cited by 22
Augraphy: A Data Augmentation Library for Document Images
Groleau, A., Chee, K. W., Larson, S., Maini, S., & Boarman, J. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-41682-8_24 · Cited by 49
Outdoor Trash Detection in Natural Environment Using a Deep Learning Model
Das, D., Deb, K., Sayeed, T., Dhar, P. K., & Shimamura, T. (2023) · IEEE Access · doi:10.1109/access.2023.3313166 · Cited by 27
“YOLOv5 uses Albumentations [52], a Python module that enables quick and versatile image augmentation.”
MethodAghayan‐Mashhady, N., & Amirkhani, A. (2023) · IET Image Processing · doi:10.1049/ipr2.12940 · Cited by 23
Selvaraj, J., & Umapathy, S. (2023) · Biomedical Physics & Engineering Express · doi:10.1088/2057-1976/ad160f · Cited by 23
A Deep Learning Image Augmentation Method for Field Agriculture
Zou, K., Shan, Y., Ran, D. C., Zhao, X., & Che, X. (2024) · IEEE Access · doi:10.1109/access.2024.3373548 · Cited by 22
A deep learning method that identifies cellular heterogeneity using nanoscale nuclear features
Carnevali, D., Zhong, L., González-Almela, E., Viana, C., Rotkevich, M., Wang, A., Franco-Barranco, D., González-Marfil, A., Neguembor, M. V., Castells-García, Á., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00883-x · Cited by 28
“Data augmentation techniques, including flipping, random rotation and colour adjustments, were applied using the Albumentations library 46 .”
Tao, W., Xie, Z., Zhang, Y., Li, J., Fu, X., Huang, J., Li, X., Su, W., & Yin, D. (2021) · Remote Sensing · doi:10.3390/rs13152903 · Cited by 24
“In addition, the regularization is used to add the index of characterizing model complexity by loss function [52].”
MethodRobust hand tracking for surgical telestration
Müller, L.-R., Petersen, J., Yamlahi, A., Wise, P. A., Adler, T. J., Seitel, A., Kowalewski, K., Müller-Stich, B. P., Kenngott, H., Nickel, F., et al. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02637-9 · Cited by 24
“We utilize the same augmentations in the Albumentations [17] as for the skeleton training.”
A First Look at Dataset Bias in License Plate Recognition
Laroca, R., dos Santos, M., Estevam, V., Luz, E. J. D. S., & Menotti, D. (2022) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi55357.2022.9991768 · Cited by 22
“Third, we used Albumentations [34], a well-known library for image augmentation, to balance the number of training images from different datasets, thus avoiding overfitting.”
MethodDivergentNets: Medical Image Segmentation by Network EnsemblePreprint
Thambawita, V. L., Hicks, S. A., Halvorsen, P., & Riegler, M. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00283 · Cited by 24
“The augmentations were implemented using the Python library Albumentations [23].”
MethodXi, J., Chen, J., Wang, Z., Ta, D., Lu, B., Deng, X., Li, X., & Huang, Q. (2021) · Ultrasonic Imaging · doi:10.1177/01617346211042526 · Cited by 21
“Finally, due to the requirement of data amount of deep learning framework, the images utilized as training data of our method are further augmented through rotating and flipping, 34 resulting in an augmented dataset whose amount is eight times greater than that of the collected dataset.”
MethodKim, J.-H., Jung, H.-S., Lee, S.-E., Hou, J., & Kwon, Y. S. (2024) · Scientific Reports · doi:10.1038/s41598-024-65060-x · Cited by 23
“Utilizing the Albumentations library— a swift and versatile data enrichment framework 23 —we applied image resizing and contrast-limited adaptive histogram equalization 24 , a method designed to adjust image contrast by expanding the histogram at both ends when the image pixels congregate around a…”
MethodMachine/deep learning‐assisted hemoglobin level prediction using palpebral conjunctival images
Kato, S., Chagi, K., Takagi, Y., Hidaka, M., Inoue, S., Sekiguchi, M., Adachi, N., Sato, K., Kawai, H., & Kato, M. (2024) · British Journal of Haematology · doi:10.1111/bjh.19621 · Cited by 21
“20 Augmented images were normalised and used as input for the model.”
Semantic Segmentation of Unmanned Aerial Vehicle Remote Sensing Images Using SegFormer
Spasev, V., Dimitrovski, I., Chorbev, I., & Kitanovski, I. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-82156-1_9 · Cited by 27
Multimodal AI and Large Language Models for Orthopantomography Radiology Report Generation and Q&A
Dasanayaka, C., Dandeniya, K., Dissanayake, M. B., Gunasena, C., & Jayasinghe, R. D. (2025) · Applied System Innovation · doi:10.3390/asi8020039 · Cited by 24
“Additionally, data augmentation techniques, particularly grid distortion and elastic transformation [39], were applied to improve the model training process and to achieve enhanced diagnostic accuracy.”
Gholinavaz, S., Saeedi, N., & Gharehveran, S. S. (2025) · Scientific Reports · doi:10.1038/s41598-025-28737-5 · Cited by 30
Fursa, I., Fandi, E., Muşat, V., Culley, J., Gil, E., Teeti, I., Bilous, L., Sluis, I. V., Rast, A. D., & Bradley, A. (2022) · SAE International Journal of Connected and Automated Vehicles · doi:10.4271/12-05-01-0008 · Cited by 32
Anomaly Detection for In situ Marine Plankton Images
Pu, Y., Feng, Z., Wang, Z., Yang, Z., & Li, J. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00409 · Cited by 25
“The random noise [4] is added to each of the normal images, and the noise is generated randomly by one of the following mechanisms, including Gaussian noise, local variance noise, Poisson noise, salt noise, pepper noise, salt and pepper noise, and speckle noise; see [3, 20, 21, 44] for details.”
BackgroundFang, L., Wu, Y., Li, Y., Guo, H., Zhang, H., Wang, X., Xi, R., & Hou, J. (2021) · Agriculture · doi:10.3390/agriculture11121190 · Cited by 24
Metadata
- Authors
- Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., & Kalinin, A. A.
- Affiliations
- Mapbox, Minsk 220030, Belarus
- Lyft (United States) (US)
- ODS.ai, Odessa 65000, Ukraine
- X5 Retail Group, Moscow 119049, Russia
- Simicon, Saint Petersburg 195009, Russia
- University of Michigan (US)
- Corresponding author
- Kalinin, Alexandr A.
- Venue
- Information
- Publisher
- MDPI AG
- Published
- 2020-02-24
- Volume
- 11
- Issue
- 2
- Pages
- 125
- ISSN
- 2078-2489 (ISSN-L)
- OpenAlex
- W2889985731
- Cited by
- 2,714
- References
- 56
- Citations by year
- 2026: 418 · 2025: 514 · 2024: 497 · 2023: 474 · 2022: 395 · 2021: 273 · 2020: 113
- FWCI
- 122.06
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Information (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Computer Science and Engineering
- Keywords
- image augmentation, Albumentations, open-source library, image transforms, data augmentation, overfitting, implicit regularization, computer vision, performance comparison
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.