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 701–800 of 1,006
Urban Sound Classification : striving towards a fair comparisonPreprint
Arnault, A., Hanssens, B., & Riche, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.11805 · Cited by 23
“Moreover, several image data augmentation techniques [19] were”
BackgroundMethodLee, H., Kim, S., Chung, H., & Kim, H. C. (2021) · Retina · doi:10.1097/iae.0000000000003190 · Cited by 15
SwiftSRGAN - Rethinking Super-Resolution for Efficient and Real-time Inference
Krishnan, K. S., & Krishnan, K. S. (2021) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta53712.2021.9689188 · Cited by 15
“The high resolution images are augmented using the albumentations [18] library.”
MethodDeep Convolutional Neural Network Approach for COVID-19 Detection
Xue, Y., Onzo, B.-M., Mansour, R. F., & Su, S. (2021) · Computer Systems Science and Engineering · doi:10.32604/csse.2022.022158 · Cited by 16
“Machine learning data augmentation is used to solve problems of class imbalance, reduce overfitting in deep learning and improve convergence [28].”
MethodDu, J., Zhang, Y., Lu, X., Zhang, M., Wang, J., Liao, S., Guo, X., & Zhao, C. (2022) · The Crop Journal · doi:10.1016/j.cj.2022.04.012 · Cited by 14
Navarro, P., Miller, L., Díaz-Galián, M. V., Gila-Navarro, A., Águila, D. J., & Egea‐Cortines, M. (2022) · GigaScience · doi:10.1093/gigascience/giac052 · Cited by 14
A domain adaptation benchmark for T1-weighted brain magnetic resonance image segmentation
Saat, P., Nogovitsyn, N., Hassan, M. Y., Ganaie, M. A., de Souza, R. M., & Hemmati, H. (2022) · Frontiers in Neuroinformatics · doi:10.3389/fninf.2022.919779 · Cited by 15
“We also applied data augmentation transformations including random rotation, shift, scaling, and cropping on 2D slices using a fast open source library named Albumentation (Buslaev et al., 2020).”
MethodHM: Hybrid Masking for Few-Shot Segmentation
Moon, S., Sohn, S. S., Zhou, H., Yoon, S., Pavlović, V., Khan, M. H., & Kapadia, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20044-1_29 · Cited by 16
“We used data augmentation for HSNetHM training on PASCAL-5 following [2, 4, 9].”
MethodKamei, M. (2023) · Smart Agricultural Technology · doi:10.1016/j.atech.2023.100372 · Cited by 14
TrueDeep: A systematic approach of crack detection with less data
Pandey, R., & Achara, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122785 · Cited by 14
Bono, A., Marani, R., Guaragnella, C., & D’Orazio, T. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108712 · Cited by 15
Eminağa, O., Saad, F., Tian, Z., Wolffgang, U., Karakiewicz, P. I., Ouellet, V., Azzi, F., Spieker, T., Helmke, B. M., Graefen, M., et al. (2024) · npj Imaging · doi:10.1038/s44303-023-00005-z · Cited by 23
Liu, X., Ono, K., & Bise, R. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105056 · Cited by 15
Han, J. H., Ha, S. Y., Lee, H., Park, G.-H., Hong, H., Kim, D., Kim, J. G., Kim, J., Sunwoo, L., Kim, C. K., et al. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2024.1442025 · Cited by 14
“The augmentation algorithm was implemented using albumentations, a Python library for image augmentations (17).”
MethodPark, T. H., & D’Amico, S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610138 · Cited by 19
“Then, during training, one of four versions is randomly selected, which is further augmented by a random set of five augmentations from the Albumentations library [62] applied in the style of RandAugment [63].”
MethodEfimov, I., Gabdulkhakov, R. R., & Rudko, V. A. (2024) · Fuel · doi:10.1016/j.fuel.2024.132725 · Cited by 16
GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning
Zhang, Y., Yu, Z., Wang, T., Huang, X., Shen, L., Gao, Z., & Ren, J. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3461958 · Cited by 25
“We employed the Albumentations [60] library to augment our data for training.”
MethodBeuse, A., Wénzel, D., Spitzer, M. S., Bartz‐Schmidt, K. U., Schultheiß, M., Poli, S., & Grohmann, C. (2024) · Ophthalmology Science · doi:10.1016/j.xops.2024.100630 · Cited by 14
Deep learning-based human gunshot wounds classification
Lira, R. Q. N., de Sousa, L. G. M., Pinho, M. L. M., Lima, R., Freitas, P. G., Dias, B. S. S., de Souza, A. C. B., & Leite, A. F. (2024) · International Journal of Legal Medicine · doi:10.1007/s00414-024-03355-4 · Cited by 18
“After discovered these augmentation techniques set, they are then incorporated in the training procedure with the Albu-mentations framework [25].”
Microstructural characterisation of fibre-hybrid polymer composites using U-Net on optical images
Dong, J. L., Kandemir, A., & Hamerton, I. (2024) · Composites Part A Applied Science and Manufacturing · doi:10.1016/j.compositesa.2024.108569 · Cited by 14
Kim, J.-I., Baek, J.-W., & Kim, C.-B. (2025) · Scientific Reports · doi:10.1038/s41598-025-88103-3 · Cited by 15
“Furthermore, to prevent overfitting, two data augmentation techniques, namely, albumentation 53 and mosaic augmentation 54 , were applied to the training dataset.”
VascX Models: Deep Ensembles for Retinal Vascular Analysis From Color Fundus Images
Quiros, J. V., Liefers, B. J., van Garderen, K. A., Vermeulen, J. P., & Klaver, C. C. W. (2025) · Translational Vision Science & Technology · doi:10.1167/tvst.14.7.19 · Cited by 14
“We observed flat performance progression on these sets before and after the chosen epoch number and did not consider it necessary to do further optimization.”
Hallström, E., Kandavalli, V. K., Wählby, C., & Hast, A. (2025) · PLoS ONE · doi:10.1371/journal.pone.0330265 · Cited by 16
“The Albumentations library [48] was used with the augmentations ShiftScaleRotate, Random-BrightnessContrast, the erasings CoarseDropout, GridDropout and PixelDropout, Blur, Hori-zontalFlip, VerticalFlip, and RandomCrop.”
Breast Tumor Cellularity Assessment Using Deep Neural Networks
Rakhlin, A., Tiulpin, A., Shvets, A. A., Kalinin, A. A., Iglovikov, V., & Nikolenko, S. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00048 · Cited by 32
Self-citationTabatabaei, S. A. H., Fischer, P., Wattendorf, S., Sabouripour, F., Howaldt, H., Wilbrand, M., Wilbrand, J.-F., & Sohrabi, K. (2021) · Scientific Reports · doi:10.1038/s41598-021-96821-7 · Cited by 14
Classification of Infection and Ischemia in Diabetic Foot Ulcers Using VGG Architectures
Güley, O., Pati, S., & Bakas, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-94907-5_6 · Cited by 21
“Especially, by taking RGB-specific augmentations [51] and preprocessing methods [52] into account, we would expect to significantly improve the model performance.”
MethodSynthetic Data Generation for the Development of 2D Gel Electrophoresis Protein Spot Models
Matuzevičius, D. (2022) · Applied Sciences · doi:10.3390/app12094393 · Cited by 14
Land Use Land Cover Labeling of GLOBE Images Using a Deep Learning Fusion Model
Manzanarez, S., Manian, V. B., & Santos, M. (2022) · Sensors · doi:10.3390/s22186895 · Cited by 14
Building Façade Style Classification from UAV Imagery Using a Pareto-Optimized Deep Learning Network
Maskeliūnas, R., Katkevičius, A., Plonis, D., Sledević, T., Meškėnas, A., & Damaševičius, R. (2022) · Electronics · doi:10.3390/electronics11213450 · Cited by 14
Deep learning for the detection of semantic features in tree X-ray CT scans
Khazem, S., Richard, A., Fix, J., & Pradalier, C. (2023) · Artificial Intelligence in Agriculture · doi:10.1016/j.aiia.2022.12.001 · Cited by 18
Boston, T., van Dijk, A. I. J. M., & Thackway, R. (2023) · Remote Sensing · doi:10.3390/rs15082132 · Cited by 15
Gassner, M., García, J. B., Tanadini‐Lang, S., Bertoldo, F., Fröhlich, F., Gückenberger, M., Haueis, S., Pelzer, C., Reyes, M., Schmithausen, P., et al. (2023) · JMIR Dermatology · doi:10.2196/42129 · Cited by 20
“Standard data augmentation techniques from the albumentations libraries [29] were applied during training to avoid overfitting.”
MethodJi, Y., Hwang, G., Lee, S. J., Lee, K., & Yoon, H. (2023) · Frontiers in Veterinary Science · doi:10.3389/fvets.2023.1236579 · Cited by 14
SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation
Li, Y., Chen, M., Wang, K., Ma, J., Bovik, A. C., & Zhang, Y. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3535456 · Cited by 19
“…resolution of 256 × 256 pixels and added the piecewise affine deformations and Gaussian noise to the generated images using the widely used Albumentations data augmentation library [43], which enabled us to evaluate the sensitivity and robustness of the compared image similarity assessment metrics.”
A CNN-Based Length-Aware Cascade Road Damage Detection Approach
Xu, H., Chen, B., & Qin, J. (2021) · Sensors · doi:10.3390/s21030689 · Cited by 14
On Attribution of DeepfakesPreprint
Zhang, B., Zhou, J., Shumailov, I., & Papernot, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.09194 · Cited by 30
“Image Augmentation: Apart from compression, we apply several image augmentation strategies obtained from the opensource albumentations library [52].”
MethodOmarov, M., Zhang, L., Jorshery, S. D., Malik, R., Das, B., Bellomo, T. R., Mansmann, U., Menten, M. J., Natarajan, P., Dichgans, M., et al. (2024) · medRxiv · doi:10.1101/2024.10.17.24315675 · Cited by 21
A computational pipeline to track chromatophores and analyze their dynamics
Ukrow, J., Renard, M. D., Moghimi, M., & Laurent, G. (2025) · eLife · doi:10.7554/elife.106509.3 · Cited by 10
A Novel Deep Learning Model for Sea State Classification Using Visual-Range Sea Images
Umair, M., Hashmani, M. A., Hussain Rizvi, S. S., Taib, H., Abdullah, M. N., & Memon, M. M. (2022) · Symmetry · doi:10.3390/sym14071487 · Cited by 13
A survey of open-access datasets for computer vision in precision poultry farming
Li, G. (2025) · Poultry Science · doi:10.1016/j.psj.2025.104784 · Cited by 18
Sketch2Process: End-to-End BPMN Sketch Recognition Based on Neural Networks
Schäfer, B., van der Aa, H., Leopold, H., & Stuckenschmidt, H. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2022.3228308 · Cited by 16
“A code listing capturing the exact pipeline we use for this, based on the Albumentations library [56], is provided in the supplementary material, available online, whereas we here focus on a description of the augmentationmethods and their relevance.”
MethodImage-Based Partial Discharge Identification in High Voltage Cables Using Hybrid Deep Network
Aldosari, O., Aldowsari, M. A., Batiyah, S. M., & Kanagaraj, N. (2023) · IEEE Access · doi:10.1109/access.2023.3278054 · Cited by 13
Abed, A., Akrout, B., & Amous, I. (2023) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-023-08159-z · Cited by 15
“…approach in computer vision for countering overfitting in deep learning models and are being used on a daily basis to improve performance [55] and for extending the amount and variety of labeled training sets through the use of input transformations that maintain the associated output…”
InfluentialSeamFormer: High Precision Text Line Segmentation for Handwritten Documents
Vadlamudi, N., Krishna, R., & Sarvadevabhatla, R. K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-41685-9_20 · Cited by 13
Suh, P. S., Jung, W., Suh, C. H., Kim, J., Oh, J., Heo, H., Shim, W. H., Lim, J., Lee, J., Kim, H. S., et al. (2023) · Frontiers in Neurology · doi:10.3389/fneur.2023.1221892 · Cited by 13
Predicting lake bathymetry from the topography of the surrounding terrain using deep learning
Martinsen, K. T., Sand‐Jensen, K., & Selvan, R. (2023) · Limnology and Oceanography Methods · doi:10.1002/lom3.10573 · Cited by 15
Enhanced Classification of Potato Leaf Disease Using Xception and ReduceLROnPlateau Callbacks
Sunyoto, A., Pristyanto, Y., & Nugraha, A. F. (2023) · IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS) · doi:10.1109/iotais60147.2023.10346045 · Cited by 13
“The problem of data imbalance class deficiency can be solved by augmenting the existing dataset [13].”
BackgroundZhu, R., Li, J., Yang, J., Sun, R., & Yu, K. (2024) · Animals · doi:10.3390/ani14040628 · Cited by 13
Fang, M., Huber, M., Fiérrez, J., Ramachandra, R., Damer, N., Alkhaddour, A., Kasantcev, M., Pryadchenko, V., Yang, Z., Huangfu, H., et al. (2023) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb57857.2023.10449130 · Cited by 17
“To enhance the model’s robustness, various data augmentations from Albumentation [8] were applied, including JPEG compression, rotation, color jitter, and blurring.”
MethodShin, S.-P., Kim, K., & Le, T. H. M. (2024) · Buildings · doi:10.3390/buildings14061808 · Cited by 13
Exploring Bi-Level Inconsistency via Blended Images for Generalizable Face Forgery Detection
Jiang, P., Xie, H., Yu, L., Jin, G., & Zhang, Y. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3417266 · Cited by 16
“For the color and frequency augmentation, we adopt RGBShift, HueSaturationValue, Ran-domBrightnessContrast, Downscale, and Sharpening from a widely used image processing toolbox [55].”
MethodA deep learning approach for high‐resolution mapping of Scottish peatland degradation
Macfarlane, F., Robb, C., Coull, M. C., McKeen, M., Wardell‐Johnson, D., Miller, D., Parker, T. C., Artz, R., Matthews, K. B., & Aitkenhead, M. J. (2024) · European Journal of Soil Science · doi:10.1111/ejss.13538 · Cited by 15
YOLO-Drone: A Scale-Aware Detector for Drone Vision
Li, Y., Ma, M., Liu, S., Yao, C., & Guo, L. (2024) · Chinese Journal of Electronics · doi:10.23919/cje.2023.00.254 · Cited by 13
Li, Y., Xia, Y., Zheng, G., Guo, X., & Li, Q. (2024) · Drones · doi:10.3390/drones8100571 · Cited by 13
Deep learning based approach for actinidia flower detection and gender assessment
Pinheiro, I., Moreira, G., Magalhães, S. A., Valente, A. L. G., Cunha, M., & dos Santos, F. N. (2024) · Scientific Reports · doi:10.1038/s41598-024-73035-1 · Cited by 14
“The augmentation operations were performed with the resource of Albumentations 24 , a Python library designed for image augmentations.”
MethodWCAY object detection of fractures for X-ray images of multiple sites
Chen, P., Liu, S., Lu, W., Lu, F., & Ding, B. (2024) · Scientific Reports · doi:10.1038/s41598-024-77878-6 · Cited by 19
Wang, L., Cui, Y., Zhang, Y., & Guo, C. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125743 · Cited by 13
Blanch, X., Jäschke, A., Elias, M., & Eltner, A. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3514854 · Cited by 13
Bae, S., Kang, K., Kim, Y. K., Jang, Y. J., & Lee, D.-H. (2025) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2025.105365 · Cited by 13
Kutlugün, M. A., Şirin, Y., & Karakaya, M. A. (2019) · Annals of Computer Science and Information Systems · doi:10.15439/2019f181 · Cited by 15
“performed a fast and efficient album creation process by performing multiple image conversion with image enhancement method [14].”
MethodData Preprocessing via Multi-sequences MRI Mixture to Improve Brain Tumor Segmentation
Groza, V., Николаевич, Т. Б., Pavlovskiy, E., Амелина, Е. Л., Amelin, M. E., Golushko, S., & Letyagin, A. Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45385-5_62 · Cited by 14
Early Detection of Malpositioned Catheters and Lines on Chest X-Rays using Deep Learning
Khan, A. B. M., & Ali, S. M. A. (2021) · International Conference on Artificial Intelligence and Computer Science Technology (ICAICST) · doi:10.1109/icaicst53116.2021.9497809 · Cited by 13
“D ATA A UGMENTATION The first step is to augment the available images using Albumentations [1] in order to have more images in the training set.”
MethodSalas, J., Vera, P., Zea-Ortiz, M., Villaseñor, E., Pulido-Arias, D., & Figueroa, A. (2021) · Remote Sensing · doi:10.3390/rs13183603 · Cited by 13
A Dual-stream Framework for 3D Mask Face Presentation Attack Detection
Shen, C., Yao, T., Zhang, K.-Y., Chen, Y., Sun, K., Ding, S., Li, J., Huang, F., & Ji, R. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00098 · Cited by 13
“All the above augmentations are implemented through the albumentations [6] library.”
BackgroundLi, F., Li, S., Fan, X., Li, X., & Chang, H. (2022) · Remote Sensing · doi:10.3390/rs14030485 · Cited by 14
Cell Nuclei Segmentation in Cryonuseg dataset using Nested Unet with EfficientNet Encoder
Dinh, T. L., Lee, S., Kwon, S.-G., & Kwon, K. (2022) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.1109/iceic54506.2022.9748537 · Cited by 13
Akhyar, F., Furqon, E. N., & Lin, C. (2022) · Sensors · doi:10.3390/s22114257 · Cited by 14
TorMentor: Deterministic dynamic-path, data augmentations with fractals
Nicolaou, A., Christlein, V., Riba, E., Shi, J., Vogeler, G., & Seuret, M. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00305 · Cited by 13
“, makes it much easier to maintain than popular frameworks such as Albumentations [2] that redefine operations for every kind of data.”
BackgroundGonçalves, B. C., Wethington, M., & Lynch, H. J. (2022) · Remote Sensing · doi:10.3390/rs14225655 · Cited by 14
Zullich, M., Macovaz, V., Pinna, G., & Pellegrino, F. A. (2023) · IEEE Access · doi:10.1109/access.2023.3236502 · Cited by 16
“…or binarized images, or even in different domains; or working with automatic augmentation techniques like those contained in Albumentations [56]) to try increasing the generalization capability of the CNN. Note that this analysis is intended as a proxy for a more complicated and…”
MethodToward Grapevine Digital Ampelometry Through Vision Deep Learning Models
Magalhães, S. A., de Castro, L. M. G., Rodrigues, L., Padilha, T. C., de Carvalho, F., dos Santos, F. N., Pinho, T. M., Moreira, G., Cunha, J., Cunha, M., et al. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3261544 · Cited by 13
“To support the data augmentation process, we used the Albumentations library [27], allowing us to change the image information and create unique data easily.”
MethodLightweight Deep Learning Model for Real-Time Colorectal Polyp Segmentation
Jeong, S.-M., Lee, S.-G., Seok, C. L., Lee, E. C., & Lee, J. (2023) · Electronics · doi:10.3390/electronics12091962 · Cited by 18
Ngo, T. K. N., Yang, S. J., Mao, B.-H., Nguyen, T. K. M., Ng, Q. D., Kuo, Y., Tsai, J.-H., Saw, S. N., & Tu, T. (2023) · Materials Today Bio · doi:10.1016/j.mtbio.2023.100820 · Cited by 19
“3 generic augmentation involved random resizing and cropping, random brightness contrast, sharpening and blurring [47].”
BackgroundAn integrated approach for magnification independent breast cancer classification
Kolla, B., & Venugopal, P. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105594 · Cited by 13
RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection
Ying, Q., Liu, J., Li, S., Xu, H., Qian, Z., & Zhang, X. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611843 · Cited by 19
“Albumentations library [24] with kernel size ranging from three to seven and 50% activation possibility (p=0.”
BackgroundSehring, J., Dohmen, H., Selignow, C., Schmid, K., Grau, S., Stein, M., Uhl, E., Mukhopadhyay, A., Németh, A., Amsel, D., et al. (2023) · Cancers · doi:10.3390/cancers15215190 · Cited by 14
“For preprocessing and data loading NumPy [43] (version 1.19.2), pandas [44] (version 1.2.4), pillow [45] (version 8.1.2), albumentations [46] (version 1.0.0), and OpenCV [47] (version 4.5.2) were used.”
MethodInfluentialCGF-Unet: Semantic Segmentation of Sidescan Sonar Based on Unet Combined With Global Features
Sun, Y., Zheng, H., Zhang, G., Ren, J., & Shu, G. (2024) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2024.3364670 · Cited by 13
“TheAlbumentationsdataenhancementtoolisusedtobuild the sidescan sonar image data set [33].”
BackgroundMatsushima, T., Noguchi, Y., Arima, J., Aoki, T., Okita, Y., Ikeda, Y., Ishimoto, K., Taniguchi, S., Yamashita, Y., Seto, S., et al. (2022) · Advanced Robotics · doi:10.1080/01691864.2022.2114297 · Cited by 13
YOLOv5 Drone Detection Using Multimodal Data Registered by the Vicon System
Lindenheim-Locher, W., Świtoński, A., Krzeszowski, T., Paleta, G., Hasiec, P., Josiński, H., Paszkuta, M., Wojciechowski, K. W., & Rosner, J. (2023) · Sensors · doi:10.3390/s23146396 · Cited by 13
“As in the previous case, a set of transformations provided by the Albumentations library [31] were implemented.”
Fehlemann, N. C., Suarez, A. L., Sandfeld, S., Bexter, F., Neite, M., Lenz, D., Könemann, M., & Münstermann, S. (2023) · steel research international · doi:10.1002/srin.202200836 · Cited by 12
Rönnau, M. M., Lepper, T. W., do AMARAL, L. D. N., Rados, P. V., & Oliveira, M. M. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107788 · Cited by 15
Deployment of Image Analysis Algorithms Under Prevalence Shifts
Godau, P., Kalinowski, P., Christodoulou, E., Reinke, A., Tizabi, M. D., Ferrer, L., Jäger, P. F., & Maier-Hein, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43898-1_38 · Cited by 21
Eversberg, L., & Lambrecht, J. (2024) · Journal of Imaging · doi:10.3390/jimaging10010016 · Cited by 17
“We used the library Albumentations [55] for online data augmentation, where we randomly performed flipping, color jitter, Gaussian noise, Gaussian blur, shifting, and scaling on training images.”
MethodImage detection model construction of Apolygus lucorum and Empoasca spp . based on improved YOLOv5
Xiong, B., Li, D., Zhang, Q., Desneux, N., Luo, C., & Hu, Z. (2024) · Pest Management Science · doi:10.1002/ps.7964 · Cited by 15
Guardia, G. S., Luijten, M., Geenen, B., Claassen, J. A. H. R., Litjens, G. J. S., de Leeuw, F., Wiesmann, M., & Kiliaan, A. J. (2024) · Scientific Reports · doi:10.1038/s41598-024-55733-y · Cited by 14
“To enhance training, we utilized both annotated and augmented data generated with the aid of Albumentations, a Python library 17 .”
MethodAutomatic labeling of fish species using deep learning across different classification strategies
Jareño, J., Bárcena‐González, G., Castro‐Gutiérrez, J., Cabrera‐Castro, R., & Galindo, P. L. (2024) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1326452 · Cited by 12
Jiang, H. T., Zhao, Z., Zhang, Z., Zhang, X., Wang, C., & Chen, X. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02388-1 · Cited by 15
“…tool library to vertically flip, rotate, and translate any input image with a probability of 0.5 and then chooses one of the processing methods such as sharpening, brightness change, Gaussian noise, and blurring at random, before performing data normalization processing (Buslaev et al. 2020).”
InfluentialBoston, T., van Dijk, A. I. J. M., & Thackway, R. (2024) · Journal of Imaging · doi:10.3390/jimaging10060143 · Cited by 17
“These results were further subdivided by vegetation class, using the 2018 label data for the tile as the reference to examine the temporal stability of each predicted model class.”
MethodGhanbari, A., Shirdel, G. H., & Maleki, F. (2024) · Algorithms · doi:10.3390/a17060267 · Cited by 18
Investigating the Sim-to-Real Generalizability of Deep Learning Object Detection Models
Rüter, J., Durak, U., & Dauer, J. C. (2024) · Journal of Imaging · doi:10.3390/jimaging10100259 · Cited by 13
“These augmentations are applied using the Albumentations library [50].”
MethodChaudhary, R., Ho, J., Smith, D., Hossain, S., Hargun, J., VanBerlo, B., Murphy, N., Prager, R. T., Rikhraj, K. J. K., Tschirhart, J. N., et al. (2025) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2025.01.041 · Cited by 12
Dual-Model Synergy for Fingerprint Spoof Detection Using VGG16 and ResNet50
Cheniti, M., Akhtar, Z., & Chandaliya, P. K. (2025) · Journal of Imaging · doi:10.3390/jimaging11020042 · Cited by 12
Chen, J., Fu, H., Lin, C., Liu, X., Wang, L., & Lin, Y. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1483824 · Cited by 21
Navigating prevalence shifts in image analysis algorithm deployment
Godau, P., Kalinowski, P., Christodoulou, E., Reinke, A., Tizabi, M. D., Ferrer, L., Jäger, P. F., & Maier-Hein, L. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103504 · Cited by 19
Boy, A. F., Akhyar, A., Arif, T. Y., & Syahrial, S. (2025) · Journal of Conservative Dentistry and Endodontics · doi:10.4103/jcde.jcde_362_25 · Cited by 12
“[26]”
Bhattacharya, S. S., Wasit, A., Earles, J. M., Nitin, N., & Yi, J. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2025.1632344 · Cited by 16
Alasmari, H., Amoudi, G., & Alghamdi, H. S. (2025) · Diagnostics · doi:10.3390/diagnostics15182301 · Cited by 13
“In the augmentation process, we used Albumentations, an open-source Python library known for its speed, flexibility, and ease of use, which offers a broader and more advanced set of transformations than most deep learning frameworks provide [38].”
The Inclusive Images Competition
Atwood, J. R., Halpern, Y., Baljekar, P. N., Breck, E. J., Sculley, D., Ostyakov, P., Nikolenko, S., Ivanov, I., Solovyev, R. A., Wang, W., et al. (2019) · The Springer series on challenges in machine learning · doi:10.1007/978-3-030-29135-8_6 · Cited by 21
Social Distancing Detection and Analysis through Computer Vision
Madane, S., & Chitre, D. (2021) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct51068.2021.9418195 · Cited by 12
“Small implementation detail is that we didn’t create a new image for each augmentation instead applied a combination of these based on specified probability with help of the Albumentations library [37].”
MethodIssifu, A. M., & Ganiz, M. C. (2021) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk52708.2021.9558986 · Cited by 19
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.