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 501–600 of 1,006
Automated Annotator Variability Inspection for Biomedical Image Segmentation
Schilling, M. P., Scherr, T., Münke, F. R., Neumann, O., Schutera, M., Mikut, R., & Reischl, M. (2022) · IEEE Access · doi:10.1109/access.2022.3140378 · Cited by 29
“We implemented our uncertainty-aware U-Net in PyTorch Lightning [47] and used data augmentation provided by Albumentations [48].”
MethodQuantitative phenotyping and evaluation for lettuce leaves of multiple semantic components
Du, J., Li, B., Lu, X., Yang, X., Guo, X., & Zhao, C. (2022) · Plant Methods · doi:10.1186/s13007-022-00890-2 · Cited by 21
“A set of image augmentation techniques [33] was applied to increase the number of leaf instances and decrease model over-fitting.”
MethodNetting Damage Detection for Marine Aquaculture Facilities Based on Improved Mask R-CNN
Zhang, Z., Gui, F., Qu, X., & Feng, D. (2022) · Journal of Marine Science and Engineering · doi:10.3390/jmse10070996 · Cited by 21
“Augmentation is generally used to improve the generalization performance of the model [29].”
Towards Robotic Marble Resin Application: Crack Detection on Marble Using Deep Learning
Vrochidou, Ε., Sidiropoulos, G. K., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., Sarafis, I. T., Kalpakis, V., & Stamkos, A. (2022) · Electronics · doi:10.3390/electronics11203289 · Cited by 22
“Semantic segmentation can provide dense pixel-level information useful to fully understand a scene.”
Esophageal Virtual Disease Landscape Using Mechanics-Informed Machine Learning
Halder, S., Yamasaki, J., Acharya, S., Kou, W., Elisha, G., Carlson, D. A., Kahrilas, P. J., Pandolfino, J. E., & Patankar, N. A. (2022) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2022.102435 · Cited by 23
“The raw cross-sectional area variation A(x, t) was augmented using a combination of grid distortional, elastic transformation, and motion blur available in the opensource Python library Albumentations [48].”
MethodVideo based oil palm ripeness detection model using deep learning
Adeta, F., & Suharjito, S. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e13036 · Cited by 23
CAD-based data augmentation and transfer learning empowers part classification in manufacturing
Ruediger-Flore, P., Glatt, M. F., Hussong, M., & Aurich, J. C. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-10973-6 · Cited by 27
MFLD-net: a lightweight deep learning network for fish morphometry using landmark detection
Saleh, A., Jones, D. B., Jerry, D. R., & Azghadi, M. R. (2023) · Aquatic Ecology · doi:10.1007/s10452-023-10044-8 · Cited by 27
“To improve the training of our network and examine its robustness to rotation, translation, scale, and noise, we apply spatial and pixel level augmentation to our training data for all models using Albumentations library (Buslaev et al. 2020).”
MethodGuan, R., Yao, S., Liu, L., Zhu, X., Man, K. L., Yue, Y., Smith, J. S., Lim, E. G., & Yue, Y. (2023) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2023.104572 · Cited by 23
Deep learning approaches for instantaneous laser absorptance prediction in additive manufacturing
Jiang, R., Smith, J., Yi, Y.-T., Sun, T., Simonds, B. J., & Rollett, A. D. (2024) · npj Computational Materials · doi:10.1038/s41524-023-01172-8 · Cited by 23
Vid2Cuts: A Framework for Enabling AI-Guided Grapevine Pruning
Häring, S., Folawiyo, S., Podguzova, M., Krauß, S., & Stricker, D. (2024) · IEEE Access · doi:10.1109/access.2024.3350432 · Cited by 25
Ticino: A multi-modal remote sensing dataset for semantic segmentation
Barbato, M. P., Piccoli, F., & Napoletano, P. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123600 · Cited by 26
Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders
Das, S., Jain, T., Reilly, D., Balaji, P., Karmakar, S., Marjit, S., Li, X., Das, A., & Ryoo, M. S. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00673 · Cited by 37
Dementyiev, V. E., Andriyanov, N. A., & Vasiliev, K. K. (2020) · 2018Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO) · doi:10.1109/synchroinfo49631.2020.9166000 · Cited by 21
“Usually in this case, one of the outputs is an artificial increase in the amount of initial data or augmentation [3,4].”
BackgroundMethodPrincipled Ultrasound Data Augmentation for Classification of Standard Planes
Lee, L. H., Gao, Y., & Noble, J. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78191-0_56 · Cited by 21
Palm Oil Counter: State-of-the-Art Deep Learning Models for Detection and Counting in Plantations
Naftali, M. G., Hugo, G., & Suharjito, S. (2024) · IEEE Access · doi:10.1109/access.2024.3419835 · Cited by 25
“To address class imbalance and enrich dataset diversity, we leverage Albumentations [55] for data augmentation.”
MethodTa, Q. T., Mac, V. H., Huh, J., Yim, H. J., & Lee, G. (2025) · Engineering Structures · doi:10.1016/j.engstruct.2025.119829 · Cited by 20
Berne, J. V., Saadi, S. B., Oliveira‐Santos, N., Marinho-Vieira, L. E., & Jacobs, R. (2025) · Journal of Dentistry · doi:10.1016/j.jdent.2025.105688 · Cited by 21
An Online Learning System for Wireless Charging Alignment Using Surround-View Fisheye Cameras
Dahal, A., Kumar, V. R., Yogamani, S. K., & Eising, C. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3182165 · Cited by 21
“As the online training data is very small, we use extensive data augmentation techniques to increase the dataset size by a factor of 30X using Albumentations [53] tool.”
MethodAlrfou, K., Kordijazi, A., Rohatgi, P. K., & Zhao, T. Q. (2022) · Materials Today Communications · doi:10.1016/j.mtcomm.2022.103174 · Cited by 20
If a human can see it, so should your system: reliability requirements for machine vision components
Hu, B. C., Marsso, L., Czarnecki, K., Salay, R., Shen, H., & Chećhik, M. (2022) · ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) · doi:10.1145/3510003.3510109 · Cited by 33
Differentiable Automatic Data Augmentation by Proximal Update for Medical Image Segmentation
He, W., Liu, M., Tang, Y., Liu, Q., & Wang, Y. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105701 · Cited by 20
Unifying Evaluation of Machine Learning Safety Monitors
Guerin, J. M., Ferreira, R., Delmas, K., & Guiochet, J. (2022) · Proceedings/Proceedings - International Symposium on Software Reliability Engineering · doi:10.1109/issre55969.2022.00047 · Cited by 31
“In particular, we generate twelve types of image perturbation presented in [19], [33], [34]: smoke, sun flare, rain, row add logic, shifted pixel, coarse dropout, grid dropout, channel shuffle, channel dropout, contrast, brightness, and Gaussian noise (see Figure 4 for examples).”
MethodPark, J.-M., Kim, U.-H., Lee, S., & Kim, J.-H. (2022) · 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/cvpr52688.2022.01338 · Cited by 32
“We implement the data augmentations with the Albumentation library [8].”
MethodDzotsenidze, E., Valla, E., Nõmm, S., Medijainen, K., Taba, P., & Toomela, A. (2022) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2022.10.240 · Cited by 21
dos Santos, D. F. D., de Faria, P. R., Travençolo, B. A. N., & do Nascimento, M. Z. (2023) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-023-00814-z · Cited by 25
“Four different augmentations based on geometric transformations were used: rotation, transpose, and horizontal and vertical axis flipping [35].”
MethodAzargoshasb, S., de Barros, H. A., Rietbergen, D. D. D., Dell’Oglio, P., van Leeuwen, P. J., Wagner, C., Stricker, P. D., Vidal‐Sicart, S., Briganti, A., Maurer, T., et al. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300192 · Cited by 20
Nuclei instance segmentation from histopathology images using Bayesian dropout based deep learning
Gudhe, N. R., Kosma, V., Behravan, H., & Mannermaa, A. (2023) · BMC Medical Imaging · doi:10.1186/s12880-023-01121-3 · Cited by 23
“To minimize over fitting, several augmentation techniques [37] were also employed during training, including horizontal and vertical flips, random rotations, and random color jitters.”
MethodAugmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset
Schaudt, D., von Schwerin, R., Hafner, A., Riedel, P., Reichert, M., von Schwerin, M., Beer, M., & Kloth, C. (2023) · Scientific Reports · doi:10.1038/s41598-023-45532-2 · Cited by 26
“All augmentations are carried out with the Albumentations library 71 .”
BackgroundTree-Based Codification in Neural Architecture Search for Medical Image Segmentation
Fuentes-Tomás, J.-A., Mezura‐Montes, E., Acosta‐Mesa, H., & Márquez-Grajales, A. (2024) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2024.3353182 · Cited by 21
“NASGP-Net was implemented based on Pytorch [58], Albumentations [59], and DEAP packages [60].”
MethodSelvaraj, J., & Jayanthy, A. K. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23034 · Cited by 20
Garcia-Salgado, B. P., Almaraz-Damian, J. A., Cervantes-Chavarria, O., Ponomaryov, V. I., Reyes-Reyes, R., Cruz-Ramos, C., & Sadovnychiy, S. (2024) · Applied Sciences · doi:10.3390/app14188183 · Cited by 23
Papa, M., Wasit, A., Pecora, J., Bergholz, T. M., & Yi, J. (2024) · Journal of Food Protection · doi:10.1016/j.jfp.2024.100430 · Cited by 20
An Efficient Solution for Semantic Segmentation of Three Ground‐based Cloud Datasets
Song, Q., Cui, Z., & Liu, P. (2020) · Earth and Space Science · doi:10.1029/2019ea001040 · Cited by 24
“These transformations can be easily implemented using the albumentation package (Buslaev et al., 2018).”
MethodLutz, B., Reisch, R. T., Kißkalt, D., Avci, B., Regulin, D., Knoll, A., & Franke, J. E. (2020) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.10.031 · Cited by 22
“For implementation, the Albumentations library [25] is used.”
MethodA Modular Region and Text Line Layout Analysis System
Kiessling, B. (2020) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr2020.2020.00064 · Cited by 20
“Regularization is performed with group normalization (G = 32) [33] after each convolutional layer.”
Method3DeepM: An Ad Hoc Architecture Based on Deep Learning Methods for Multispectral Image Classification
Navarro, P., Miller, L., Gila-Navarro, A., Díaz-Galián, M. V., Águila, D. J., & Egea‐Cortines, M. (2021) · Remote Sensing · doi:10.3390/rs13040729 · Cited by 20
ClipAssistNet: bringing real-time safety feedback to operating rooms
Aspart, F., Bolmgren, J. L., Lavanchy, J. L., Beldi, G., Woods, M. S., Padoy, N., & Hosgor, E. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02441-x · Cited by 23
“Image preprocessing is performed using the albumentations library [7].”
MethodAutomated measurement of Vickers hardness using image segmentation with neural networks
Li, Z., & Yin, F. (2021) · Measurement · doi:10.1016/j.measurement.2021.110200 · Cited by 20
Chest X-ray abnormalities localization via ensemble of deep convolutional neural networks
Pham, V. T., Tran, C.-M., Zheng, S., Minh, V. T., & Nath, S. (2021) · International Conference on Advanced Technologies for Communications · doi:10.1109/atc52653.2021.9598342 · Cited by 33
General Purpose (GenP) Bioimage Ensemble of Handcrafted and Learned Features with Data AugmentationPreprint
Nanni, L., Brahnam, S., Ghidoni, S., & Maguolo, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08084 · Cited by 25
Image Stylization for Robust FeaturesPreprint
Melekhov, I., Brostow, G., Kannala, J., & Turmukhambetov, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.06959 · Cited by 27
“For color augmentation we use Albumentations [5] library to generate random color transforms of training images.”
MethodMoiré pattern removal via attentive fractal network
Xu, D., Chu, Y., & Sun, Q. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00244 · Cited by 19
“The CFAMoir´e [39] dataset contains images of size 128 × 128 , and we augment the training data with random flips, 90 ◦ rotations and Ran-domResizedCrop from albumentations [3].”
MethodWang, Z., Chen, Y., Shang, Y., Yang, X., Pan, W., Ye, X., Sakurai, T., & Zeng, X. (2025) · BMC Biology · doi:10.1186/s12915-025-02166-2 · Cited by 20
“For the image modality, cyclic peptide images were randomly augmented using the following methods (implemented via the Albumen-tations Python library [44]): random rotation, cropping and padding, scaling, blurring, Gaussian noise injection, and salt-and-pepper noise injection.”
Sheth, F., Chatter, I., Jasra, M., Kumar, G., & Sharma, R. (2025) · Plant Methods · doi:10.1186/s13007-025-01421-5 · Cited by 23
“These augmentations were implemented using the Albumentations library in Python, which supports a range of robust, efficient image transformation methods [53].”
Broad Dataset and Methods for Counting and Localization of On-Ear Corn Kernels
Hobbs, J. A., Khachatryan, V., Anandan, B. S., Hovhannisyan, H., & Wilson, D. L. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.627009 · Cited by 19
“All other parameters not noted here are the default parameters given in Buslaev et al. (2020).”
BackgroundMethodSemi-supervised adversarial discriminative domain adaptation
Nguyen, T.-V., Nguyen, A., Le, T. N., & Le, B. H. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04288-4 · Cited by 22
MyopiaDETR: End-to-end pathological myopia detection based on transformer using 2D fundus images
Li, M., Liu, S., Wang, Z., Li, X. S., Yan, Z., Zhu, R., & Wan, Z. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1130609 · Cited by 20
“As for the data augmentation implementation approach, we adopt the image processing algorithms based on opencv-python and Albumentations library (Buslaev et al., 2020).”
MethodAkingbesote, D., Zhan, Y., Maskeliūnas, R., & Damaševičius, R. (2023) · Algorithms · doi:10.3390/a16060292 · Cited by 24
A VAN-Based Multi-Scale Cross-Attention Mechanism for Skin Lesion Segmentation Network
Liu, S., Zhuang, Z., Zheng, Y., & Kolmaniè, S. (2023) · IEEE Access · doi:10.1109/access.2023.3298826 · Cited by 22
“the Albumentations library [38], including randomflips, rotations, scaling, occlusions, and Gaussian blurring.”
BackgroundAugmentation-based Domain Generalization for Semantic Segmentation
Schwonberg, M., Bouazati, F. E., Schmidt, N. M., & Gottschalk, H. (2023) · 2023 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/iv55152.2023.10186752 · Cited by 17
Cano-Solis, M., Ballesteros, J. R., & Branch, J. W. (2023) · Data · doi:10.3390/data8080128 · Cited by 19
Rosenberger, J., Tlatlik, J., & Münstermann, S. (2023) · Engineering Fracture Mechanics · doi:10.1016/j.engfracmech.2023.109686 · Cited by 19
“Specifically, the dataloader was customized to ensure compatibility with our used image format and the tailored augmentation pipelines implemented with Albumentations [26].”
MethodInfluentialSimultaneous Object Detection and Distance Estimation for Indoor Autonomous Vehicles
Azurmendi, I., Zulueta, E., López-Guede, J. M., & González, M. (2023) · Electronics · doi:10.3390/electronics12234719 · Cited by 21
AIoT-Based Meat Quality Monitoring Using Camera and Gas Sensor With Wireless Charging
Kim, D.-E., Mai, N.-D., & Chung, W. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3328915 · Cited by 19
Schaudt, D., Späte, C., von Schwerin, R., Reichert, M., von Schwerin, M., Beer, M., & Kloth, C. (2023) · Bioengineering · doi:10.3390/bioengineering10121421 · Cited by 25
“Augmentations are carried out by the Albumentations library [57].”
BackgroundGRMPose: GCN-based real-time dairy goat pose estimation
Chen, L., Zhang, L., Tang, J., Tang, C., An, R., Han, R., & Zhang, Y. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108662 · Cited by 24
NDELS: A Novel Approach for Nighttime Dehazing, Low-Light Enhancement, and Light Suppression
Bernabel, S., & Agaian, S. С. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3388420 · Cited by 22
Marini, N., Marchesin, S., Wodziński, M., Caputo, A., Podareanu, D., Guevara, B. C., Boytcheva, S., Vatrano, S., Fraggetta, F., Ciompi, F., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103303 · Cited by 23
Sangaiah, A. K., Anandakrishnan, J., Devarapelly, A. R., Mohamad, M. L. A. B., Bian, G., Alenazi, M. J. F., & AlQahtani, S. A. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3452053 · Cited by 19
“The PyTorch “ albumentations ” library produced augmented data and the corresponding annotation data [40].”
Buławka, N., Orengo, H. A., & Berganzo‐Besga, I. (2024) · Journal of Archaeological Science · doi:10.1016/j.jas.2024.106053 · Cited by 20
Ullah, I., Chikontwe, P., & Park, S. H. (2019) · IEEE Access · doi:10.1109/access.2019.2950263 · Cited by 20
“created using transformations [48] such as scaling (from 0.”
MethodMRI Brain Tumor Segmentation Using a 2D-3D U-Net Ensemble
Asenjo, J. M., & Martinez-Larraz, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72084-1_32 · Cited by 22
Detecting COVID-19 Opacity in X-ray Images Using YOLO and RetinaNet Ensemble
Tiwari, V., Singhal, A., & Dhankhar, N. (2022) · IEEE Delhi Section Conference (DELCON) · doi:10.1109/delcon54057.2022.9753272 · Cited by 20
“Albumentations library [22] has been used to apply augmentations.”
MethodDetecting clinical medication errors with AI enabled wearable cameras
Chan, J., Nsumba, S., Wortsman, M., Dave, A., Schmidt, L., Gollakota, S., & Michaelsen, K. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01295-2 · Cited by 18
Rivera, Z. C., González-Seguel, F., Horikawa-Strakovsky, A., Granger, C. L., Sarwal, A., Dhar, S., Ntoumenopoulos, G., Chen, J., Bumgardner, C., Parry, S. M., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-99522-7 · Cited by 23
“Spatial and strong color data augmentation was also used and was performed using Albumentations 47 , a python library used for image augmentation in computer vision tasks.”
Deepfake Detection using Capsule Networks and Long Short-Term Memory Networks
Mehra, A., Spreeuwers, L., & Strisciuglio, N. (2021) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010289004070414 · Cited by 19
“As augmentation makes the model robust, we perform additional augmentations provided by Albumentations (Buslaev et al., 2020).”
MethodEnd-to-End Optical Character Recognition for Bengali Handwritten Words
Safir, F. B., Ohi, A. Q., Mridha, M. F., Monowar, M. M., & Hamid, M. A. (2021) · National Computing Colleges Conference (NCCC) · doi:10.1109/nccc49330.2021.9428809 · Cited by 19
SCSS-Net: solar corona structures segmentation by deep learning
Mackovjak, Š., Harman, M., Krešňáková, V., & Butka, P. (2021) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stab2536 · Cited by 20
Evaluating generic AutoML tools for computational pathology
Schwen, L. O., Schacherer, D. P., Geißler, C., & Homeyer, A. (2022) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2022.100853 · Cited by 28
A multi-category intelligent method for the evaluation of visual comfort in underground space
Zhou, B., Gui, Y., Xie, X., Li, W., & Li, Q. (2022) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2022.104488 · Cited by 18
Core box image recognition and its improvement with a new augmentation technique
Baraboshkin, E. E., Demidov, A. E., Orlov, D., & Koroteev, D. A. (2022) · Computers & Geosciences · doi:10.1016/j.cageo.2022.105099 · Cited by 18
Ensemble Deep Learning for Human-Object Interaction Detection
Mansour, A. E., Mohammed, A., Elsayed, H. A. E. A., & Ramly, S. H. E. (2022) · International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC) · doi:10.1109/miucc55081.2022.9781774 · Cited by 18
de Oro, J. E. C. G., Koch, P. J., Krois, J., Ros, A. G. C., Patel, J. S., Meyer‐Lueckel, H., & Schwendicke, F. (2022) · Diagnostics · doi:10.3390/diagnostics12071526 · Cited by 18
Deep 360$$^\circ $$ Optical Flow Estimation Based on Multi-projection Fusion
Li, Y., Barnes, C., Huang, K., & Zhang, F. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19833-5_20 · Cited by 27
Feasibility of Automated Black Ice Segmentation in Various Climate Conditions Using Deep Learning
Lee, S.-Y., Jeon, J.-S., & Le, T. H. M. (2023) · Buildings · doi:10.3390/buildings13030767 · Cited by 19
Automatic Building Height Estimation: Machine Learning Models for Urban Image Analysis
Ureña-Pliego, M., Marín, R. M., González-Rodrigo, B., & Marchamalo, M. (2023) · Applied Sciences · doi:10.3390/app13085037 · Cited by 19
“Data augmentation addresses the issue of a lack of generalisation and consists of altering the input images of a dataset, thus creating new data from the existing dataset [37].”
BackgroundToward improved surveillance of Aedes aegypti breeding grounds through artificially augmented data
Passos, W. L., Barreto, C. D. S., Araújo, G., Haque, U., Netto, S. L., & da Silva, E. A. B. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106488 · Cited by 18
Karanowski, K., Chłopowiec, A. R., Skrzypczak, T., Grzesiuk, M., Chłopowiec, A. B., & Tabakov, M. (2023) · Diagnostics · doi:10.3390/diagnostics13111904 · Cited by 24
AttResDU-Net: Medical Image Segmentation Using Attention-based Residual Double U-Net
Khan, A. M., Ashrafee, A., Khan, F. S., Hasan, M. B., & Kabir, M. H. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191528 · Cited by 24
“Random rotation, vertical and horizontal flip, Hue Saturation Value (HSV) conversion, random brightness-contrast, and histogram equalization were among the data augmentation techniques we applied to each of the datasets to increase the dataset sizes by six-fold using the augmentation tool: Albumentations [30].”
MethodSelvaraj, J., & Jayanthy, A. K. (2023) · Biomedical Engineering Applications Basis and Communications · doi:10.4015/s1016237223500266 · Cited by 20
Low-quality image object detection based on reinforcement learning adaptive enhancement
Ye, J., Wu, Y., & Peng, D. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.04.019 · Cited by 18
Габдуллин, М. Т., Mukasheva, A., Koishiyeva, D., Umarov, T., Bissembayev, A., Kim, K.-S., & Kang, J. W. (2024) · Biotechnology and Bioprocess Engineering · doi:10.1007/s12257-024-00130-5 · Cited by 18
“This metric was used to quantify the similarity between true A and predicted B model nuclei [54].”
Schneider, F., Swiatek, J., & Jelali, M. (2024) · Sustainability · doi:10.3390/su16156420 · Cited by 21
Image augmentation approaches for small and tiny object detection in aerial images: a review
Nisa, U. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19768-7 · Cited by 24
Poses of People in Art: A Dataset for Human Pose Estimation in Digital Art History
Schneider, S., & Vollmer, R. (2024) · Journal on Computing and Cultural Heritage · doi:10.1145/3696455 · Cited by 21
“During training, we adopted the following data augmentation techniques from the Albumentations library [9] to increase the models’ robustness: (i) either RandomBrightnessContrast or CLAHE is applied with a probability of p = 0.”
MethodAccelerating weed detection for smart agricultural sprayers using a Neural Processing Unit
Herterich, N., Liu, K., & Stein, A. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110608 · Cited by 18
The Impact of Padding on Image Classification by Using Pre-trained Convolutional Neural Networks
Tang, H., Ortis, A., & Battiato, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30645-8_31 · Cited by 23
A load frame for in situ tomography at PETRA III
Moosmann, J. P., Wieland, D. C. F., Zeller‐Plumhoff, B., Galli, S., Krüger, D., Ershov, A., Lautner, S., Sartori, J., Dean, M. N., Köhring, S., et al. (2019) · Developments in X-Ray Tomography · doi:10.1117/12.2530445 · Cited by 21
Challenges in the deep learning-based semantic segmentation of benthic communities from Ortho-images
Pavoni, G., Corsini, M., Pedersen, N. E., Petrovic, V., & Cignoni, P. (2020) · Applied Geomatics · doi:10.1007/s12518-020-00331-6 · Cited by 20
“The Albumentations library [1] offers a valid implementation of on-line color augmentation transformations.”
BackgroundSegmentation and Defect Classification of the Power Line Insulators: A Deep Learning-based Approach
Alahyari, A., Hinneck, A., Tariverdizadeh, R., & Pozo, D. (2020) · International Conference on Smart Grids and Energy Systems (SGES) · doi:10.1109/sges51519.2020.00090 · Cited by 18
“To do so, we used different types of augmentations by albumentation [19] such as HorizontalFlip, VerticalFlip, BrightnessContrast, and others, complete list of which is given in Table II.”
Koehler, S., Hussain, T., Blair, Z., Huffaker, T., Ritzmann, F., Tandon, A. A., Pickardt, T., Sarikouch, S., Latus, H., Greil, G., et al. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3052972 · Cited by 22
Sketch2BPMN: Automatic Recognition of Hand-Drawn BPMN Models
Schäfer, B., van der Aa, H., Leopold, H., & Stuckenschmidt, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-79382-1_21 · Cited by 18
Learning an augmentation strategy for sparse datasets
Arantes, R. B., Vogiatzis, G., & Faria, D. R. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104338 · Cited by 20
Online Monitoring of Object Detection Performance During Deployment
Rahman, Q. M., Sünderhauf, N., & Dayoub, F. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635940 · Cited by 27
Tian, D., Zhu, B., Wang, J., Kong, L., Gao, B., Wang, Y., Xu, D., Zhang, R., & Yao, Y. (2022) · IEEE Access · doi:10.1109/access.2022.3196356 · Cited by 25
“In this study, we use the Albumentations library [27] to perform data augmentation operations, which efficiently implements various image transformation operations.”
MethodNitze, I., Heidler, K., Nesterova, N., Küpper, J., Schütt, E., Hölzer, T., Barth, S., Lara, M. J., Liljedahl, A., & Grosse, G. (2025) · Scientific Data · doi:10.1038/s41597-025-05810-2 · Cited by 18
“For augmentation we used the albumentations python package (Buslaev et al., 2020) (Buslaev et al., 2020) .”
Adapting the segment anything model for multi-modal retinal anomaly detection and localization
Li, J., Chen, T., Wang, X., Zhong, Y., & Xiao, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102631 · Cited by 27
DSF-YOLO for robust multiscale traffic sign detection under adverse weather conditions
Li, J., Deng, Q., Gao, W., Yang, B., Jia, L., Zhou, J., & Pu, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-02877-0 · Cited by 21
Vollmer, E., Ruck, J., Volk, R., & Schultmann, F. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.06.006 · Cited by 21
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.