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 801–900 of 1,006
Real-Time Monitoring of COVID-19 SOP in Public Gathering Using Deep Learning Technique
Khel, M. H. K., Kadir, K., Albattah, W., Khan, S., Noor, M., Nasir, H., Habib, S., Islam, M., & Khan, A. (2021) · Emerging Science Journal · doi:10.28991/esj-2021-sper-14 · Cited by 12
Ballesteros, J. R., Torres, G. S., & Branch, J. W. (2022) · Data · doi:10.3390/data7040050 · Cited by 15
“Data augmentation tends to improve model generalization [2,10,19,23,24], increasing the number of available examples to train a model.”
BackgroundMethodInfluentialKoskela, O., Pereira, L. S. B., Pölönen, I., Aronen, I., & Kunttu, I. (2022) · Agricultural and Food Science · doi:10.23986/afsci.111665 · Cited by 12
“The software used included Python (version 3.6.9), Keras (version 2.2.4) with backend TensorFlow (version 1.14.0), Keras-vis toolkit (version 0.4.1), Albumentations image augmentation library (version 0.4.2) (Buslaev et al. 2020), and opencv-python (version 3.4.2.17) computer vision library (Bradski 2000).”
MethodInfluentialZhao, Z., & Wu, T. (2022) · Scientific Programming · doi:10.1155/2022/4385565 · Cited by 13
“Buslaev processes multiple images separately and merges them into one image, extracts features from it and the previous processing steps, establishes the feature space of the learning classifier based on artificial neural network, and performs automatic detection and classification [9].”
BackgroundDevelopment of a Productive Transport Detection System Using Convolutional Neural Networks
Andriyanov, N. A., Dementiev, V., & Ташлинский, А. Г. (2022) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661822030038 · Cited by 12
EffResUNet: Encoder Decoder Architecture for Cloud-Type Segmentation
Nalwar, S., Shah, K., Bidwe, R. V., Zope, B., Mane, D., Jadhav, V., & Shaw, K. (2022) · Big Data and Cognitive Computing · doi:10.3390/bdcc6040150 · Cited by 12
“This is why we opted for Albumentations [22], a real-time augmentation library that generates high-quality transformed images.”
UAV-ODS: A Real-time Outfall Detection System Based on UAV Remote Sensing and Edge Computing
Xu, H., Huang, Q., Yang, Y., Li, J., Chen, X., Han, W., & Wang, L. (2022) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus55513.2022.9987107 · Cited by 12
“The enhancement methods include both pixel-level and spatial-level methods, which are implemented using the Albumentations library [10].”
MethodMarkodimitrakis, E., Lin, S., Koutoulakis, E., Marín-Castrillón, D. M., Sáez, F. A. T., Leclerc, S., Bernard, C., Boucher, A., Presles, B., Bouchot, O., et al. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12020402 · Cited by 12
CISA: Context Substitution for Image Semantics Augmentation
Nesteruk, S., Zherebtsov, I., Illarionova, S., Shadrin, D., Somov, A., Bezzateev, S. V., Yelina, T. N., Денисенко, В. В., & Oseledets, I. V. (2023) · Mathematics · doi:10.3390/math11081818 · Cited by 13
Karthik, R., Menaka, R., Siddharth, M. V., Hussain, S., Bala Murugan, M. S., & Won, D. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08943-w · Cited by 12
“The following augmentations were carried out using the Albumentations [4] library: (1) random portions of an image were cropped and resized to a given size; 2) randomly transposing the input images; 3) randomly flipping the images horizontally and vertically; 4) random affine transformations were applied on input imag…”
MethodInfluentialClueCatcher: Catching Domain-Wise Independent Clues for Deepfake Detection
Lee, E.-G., Lee, I., & Yoo, S. B. (2023) · Mathematics · doi:10.3390/math11183952 · Cited by 17
Boosted Additive Angular Margin Loss for breast cancer diagnosis from histopathological images
Alirezazadeh, P., & Dornaika, F. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107528 · Cited by 12
Wang, F., Fu, X., Duan, W., Wang, B., & Li, H. (2023) · Agriculture · doi:10.3390/agriculture13102011 · Cited by 12
Callejo, M. Á. M., Cira, C.-I., Justel, J. J. A., Sínde-González, I., & Sălăgean, T. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2023.103563 · Cited by 20
Image-based classification of wheat spikes by glume pubescence using convolutional neural networks
Artemenko, N. V., Александрович, Г. М., Epifanov, R., Komyshev, E. G., Kruchinina, Y. V., Koval, V. S., Гончаров, Н. П., & Afonnikov, D. A. (2024) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1336192 · Cited by 15
2 nd Workshop on Maritime Computer Vision (MaCVi) 2024: Challenge Results
Kiefer, B., Žust, L., Kristan, M., Perš, J., Teršek, M., Wiliem, A., Messmer, M., Yang, C.-Y., Huang, H.-W., Jiang, Z., et al. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00099 · Cited by 21
Federated Versus Central Machine Learning on Diabetic Foot Ulcer Images: Comparative Simulations
Saeedi, M., Gorji, H. T., Vasefi, F., & Tavakolian, K. (2024) · IEEE Access · doi:10.1109/access.2024.3392916 · Cited by 12
Pavement Defect Segmentation in Orthoframes with a Pipeline of Three Convolutional Neural Networks
Lõuk, R., Riid, A., Pihlak, R., & Tepljakov, A. (2020) · Algorithms · doi:10.3390/a13080198 · Cited by 13
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning ChallengesPreprint
Bruintjes, R.-J., Lengyel, A., Baptista-Ríos, M., Kayhan, O. S., & van Gemert, J. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03768 · Cited by 24
“The Albumentations library [5], the AutoAugment policies [77] and the”
MethodOil Palm Fruits Dataset in Plantations for Harvest Estimation Using Digital Census and Smartphone
Suharjito, S., Naftali, M. G., Hugo, G., Priyadi, M. R. A., Asrol, M., & Utama, D. N. (2025) · Scientific Data · doi:10.1038/s41597-025-05227-x · Cited by 12
“To address class imbalance and enhance data variation, data augmentation techniques were applied using the Albumentations library 8 .”
Sailer, S., Mundszinger, M., Martin, J., Mancini, M., Wohlfahrt‐Mehrens, M., & Kaiser, U. A. (2022) · Micron · doi:10.1016/j.micron.2022.103398 · Cited by 11
Korznikov, K., Kislov, D. E., Petrenko, T. Y., Dzizyurova, V. D., Doležal, J., Krestov, P. V., & Altman, J. (2023) · Remote Sensing · doi:10.3390/rs15184394 · Cited by 14
Müller, L., Tibyampansha, D., Mildenberger, P., Panholzer, T., Jungmann, F., & Halfmann, M. C. (2023) · BMC Medical Imaging · doi:10.1186/s12880-023-01142-y · Cited by 15
“5.2, https:// album entat ions. ai) [25].”
InfluentialChoudhary, A. K., Grubesa, T., Jansche, A., Bernthaler, T., Goll, D., & Schneider, G. (2023) · Acta Materialia · doi:10.1016/j.actamat.2023.119563 · Cited by 11
Multiscale Attention-Based Instance Segmentation for Measuring Crystals With Large Size Variation
Neubauer, T., Berg, A., Wimmer, M., Lenis, D., Major, D., Winter, P. M., Paolis, G. R. D., Novotny, J., Lüftner, D., Reinharter, K., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3345916 · Cited by 12
“(6) We use additional training augmentation by adding random brightness and contrast from the albumentations library [41] to the image.”
MethodAn Overview on Data Augmentation for Machine Learning
Volkova, S. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-55349-3_12 · Cited by 12
Cormier, M., Specker, A., Jacques, J. C. S., Moritz, L., Metzler, J., Moeslund, T. B., Nasrollahi, K., Escalera, S., & Beyerer, J. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw60836.2024.00044 · Cited by 11
“Finally, the authors use the Albumentations Library [2] Affine, HonrizontalFlip and CoarseDropout.”
Paniego, S., Calvo-Palomino, R., & Cañas, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128161 · Cited by 12
MixCDNet: A Lightweight Change Detection Network Mixing Features Across CNN and Transformer
Wang, L., Zhang, J., & Bruzzone, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3438228 · Cited by 13
Skin Tone Analysis Through Skin Tone Map Generation With Optical Approach and Deep Learning
Jung, G., Kim, S., & Yoo, S. (2024) · Skin Research and Technology · doi:10.1111/srt.70088 · Cited by 11
“We employed a batch size of 12 and cross-entropy loss, with data augmentation performed using the Albumentations library [28], incorporating techniques such as horizontal flip, shift-scale rotation, random crop, hue saturation, random brightness contrast, unsharp mask, and image compression.”
MethodDistributed Intelligent Video Surveillance for Early Armed Robbery Detection Based on Deep Learning
Fernandez-Testa, S., & Salcedo, E. (2024) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi62404.2024.10716299 · Cited by 11
“Specifically, we applied jointly two of the HorizontalFlip , ShiftScaleRotate , RandomBrightnessContrast , CLAHE , Affine , and RandomResizedCrop functions of the Albumentations library [21] to create new video samples.”
MethodDataset Enhancement with Instance-Level Augmentations
Kupyn, O., & Rupprecht, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73337-6_22 · Cited by 27
Spatial-temporal attention for video-based assessment of intraoperative surgical skill
Wan, B., Peven, M., Hager, G. D., Sikder, S., & Vedula, S. S. (2024) · Scientific Reports · doi:10.1038/s41598-024-77176-1 · Cited by 12
Alshagathrh, F. M., Alzubaidi, M. S., Gecík, S., Alswat, K., Aldhebaib, A., Alahmadi, B., Alkubeyyer, M., Alosaimi, A., Alsadoon, A., Alkhamash, M., et al. (2024) · Diagnostics · doi:10.3390/diagnostics14232646 · Cited by 11
Wu, Q., Qin, X., & Xiong, X. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103169 · Cited by 11
Li, P., Zhang, Y., Yang, Q., Li, T., & Chen, Z. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109772 · Cited by 15
“Strong augmentation (Buslaev et al., 2020) is applied using random flip, optical blur, random rotate, color jitter, grid dropout, and normalization strategies.”
Afzaal, H., Rude, D., Farooque, A. A., Randhawa, G. S., Schumann, A. W., & Krouglicof, N. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.100934 · Cited by 16
Image segmentation of treated and untreated tumor spheroids by fully convolutional networks
Streller, M., Michlíková, S., Ciecior, W., Lönnecke, K., Kunz‐Schughart, L. A., Lange, S., & Voß-Böhme, A. (2025) · GigaScience · doi:10.1093/gigascience/giaf027 · Cited by 12
“Since this increases the total amount of training data, data augmentation can impr ov e performance and avoid overfitting [ 61 ].”
Sun, S., Yin, Z., Cleave, J. G. V., Wang, L., Fried, B., Bilal, K. H., Lucas, F. M., İşgör, İ. Ş., Webb, D. C., Singi, S., et al. (2025) · Science Translational Medicine · doi:10.1126/scitranslmed.adq2162 · Cited by 14
Best practices for AI-based image analysis applications in aquatic sciences: The iMagine case study
Azmi, E., Alibabaei, K., Kozlov, V. Y., Krijger, T., Accarino, G., Ayata, S., Calatrava, A., Carlo, M. M. D., Decrop, W., Elia, D., et al. (2025) · Ecological Informatics · doi:10.1016/j.ecoinf.2025.103306 · Cited by 13
“Users can customize the train/validation/test split according to their preferences and apply data augmentation using the Python Albumentations package (Buslaev et al., 2020).”
YOLO-PICO: Lightweight object recognition in remote sensing images using expansion attention modules
Aghili, M. E., Ghassemian, H., & Imani, M. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.113114 · Cited by 16
Overlap Training to Mitigate Inconsistencies Caused by Image Tiling in CNNs
An, Y., Ye, Q., Guo, J., & Dong, R. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63799-6_3 · Cited by 11
Semi-Supervised Learning for Cervical Precancer Detection
Angara, S., Guo, P. W., Xue, Z., & Antani, S. (2021) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms52027.2021.00072 · Cited by 14
Source Camera Model Identification
Mandelli, S., Bonettini, N., & Bestagini, P. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-16-7621-5_7 · Cited by 18
Sample-Efficient Deep Learning Techniques for Burn Severity Assessment with Limited Data Conditions
Shin, H., Shin, H., Choi, W., Park, J., Park, M., Koh, E., & Woo, H. (2022) · Applied Sciences · doi:10.3390/app12147317 · Cited by 12
Document Recapture Detection Based on a Unified Distortion Model of Halftone Cells
Hu, Z., Chen, C., Mow, W. H., & Huang, J. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3192999 · Cited by 12
Pham, V.-T.-N., Nguyen, Q.-C., & Nguyen, Q.-V. (2022) · Vietnam Journal of Computer Science · doi:10.1142/s2196888822500348 · Cited by 12
Zhou, Z. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/7078670 · Cited by 11
“Data augmentation can artificially expand the dataset, increase the diversity of the data, and improve the robustness of the model [23].”
BackgroundThe Effect of Data Augmentation Methods on Pedestrian Object Detection
Liu, B., Su, S., & Wei, J. (2022) · Electronics · doi:10.3390/electronics11193185 · Cited by 11
“We use the MSRS public dataset.”
Cui, H., Li, Y., Jiang, L., Wang, Y., Xia, Y., & Zhang, Y. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106218 · Cited by 11
Ingle, A., Roja, M. M., Sankhe, M. S., & Patkar, D. (2022) · International journal of electrical and computer engineering systems · doi:10.32985/ijeces.13.8.4 · Cited by 11
“To address the scarcity of data the data augmentation technique is used to raise the dataset artificially from the existing training dataset by applying random transformations which provide a diversity of data available for the training model [4, 5].”
MethodA compact CNN model for automated detection of COVID-19 using thorax x-ray images
Awan, T., Khan, K. B., & Mannan, A. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-223704 · Cited by 12
Dan, R., Li, Y., Wang, Y., Chen, X.-D., Jia, G., Wang, S., Ge, R., Qian, G., Jin, Q., Ye, J., et al. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3271696 · Cited by 11
“Specifically, we implement the common data augmentation mechanism via a widely-used tool [55].”
MethodAnomaly Segmentation for High-Resolution Remote Sensing Images Based on Pixel Descriptors
Li, J., Wang, X., Zhao, H., Wang, S., & Zhong, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25563 · Cited by 11
Pora, W., Kasamsumran, N., Tharawatcharasart, K., Ampol, R., Siriyasatien, P., & Jariyapan, N. (2023) · PLoS ONE · doi:10.1371/journal.pone.0284330 · Cited by 12
“We employed data augmentation or image augmentation [29] to expand the original dataset artificially to train our deep neural networks.”
MethodMicrostructure quality control of steels using deep learning
Durmaz, A. R., Potu, S. T., Romich, D., Möller, J. J., & Nützel, R. (2023) · Frontiers in Materials · doi:10.3389/fmats.2023.1222456 · Cited by 13
Spatio-Temporal Catcher: A Self-Supervised Transformer for Deepfake Video Detection
Li, M., Li, X., Yu, K., Deng, C. D., Huang, H., Mao, F., Xue, H., & Li, M. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613842 · Cited by 22
“We adopt the RGBShift, HueSaturation, RandomBrightnessContrast, Downscale, and Sharpen from a widely used toolbox [9] for data augmentation.”
MethodSchut, D. E., Wood, R. M., Trull, A. K., Schouten, R. E., van Liere, R., van Leeuwen, T., & Batenburg, K. J. (2024) · Postharvest Biology and Technology · doi:10.1016/j.postharvbio.2024.112814 · Cited by 13
“Data augmentation was applied to the training data using the ColorJitter , ShiftScaleRotate and GaussNoise functions of the Albumentations package (Buslaev et al., 2020).”
MethodAdaptive Augmentation of Imbalanced Class Distribution in Road Segmentation
Khan, M. R. K., Islam, M. S., Porna, S. B., Kamara, A. A., Hossain, M., & Rafi, A. H. (2023) · International Conference on Electrical, Communication, and Computer Engineering (ICECCE) · doi:10.1109/icecce61019.2023.10442626 · Cited by 11
“The data passed through to the ADA module and the albumentations tool [11] for augmentation is further split into training (80%), validation (10%), and testing (10”
BackgroundMethodThe hawk eye scan: Halyomorpha halys detection relying on aerial tele photos and neural networks
Palazzetti, L., Rangarajan, A. K., Dinca, A., Boom, B., Popescu, D., Offermans, P., & Pinotti, C. M. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.109365 · Cited by 11
OpenAnimalTracks: A Dataset for Animal Track Recognition
Shinoda, R., & Shiohara, K. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10648043 · Cited by 16
GridMask Based Data Augmentation For Bengali Handwritten Grapheme Classification
Yang, J. (2020) · International Conference on Intelligent Medicine and Image Processing (IMIP) · doi:10.1145/3399637.3399650 · Cited by 11
“We use Pytorch to implement the network architecture design and the Albumentations python library [2] toolkit package to implement the data augmentation approaches.”
MethodApplication of shared backbone DNNs in ADAS perception systems
Lobanov, M. G., & Sholomov, D. L. (2021) · International Conference on Machine Vision · doi:10.1117/12.2586932 · Cited by 12
“To improve the robustness of the network, the images were augmented by the Albumentations library [21] with blur, random gamma, random brightness and contrast, Gaussian noise, Jpeg compression and augmentation in HSV color space.”
MethodEfficient Palm-Line Segmentation with U-Net Context Fusion Module
Văn, T. P., Nguyen, S. T., Doan, L. B., Tran, N., & Thanh, T. M. (2020) · International Conference on Advanced Computing and Applications (ACOMP) · doi:10.1109/acomp50827.2020.00011 · Cited by 11
Data Augmentation for JPEG Steganalysis
Itzhaki, T., Yousfi, Y., & Fridrich, J. (2021) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs53200.2021.9648390 · Cited by 11
“We use the Albumentations Library [7] as well as custom augmentations specifically designed for steganalysis.”
MethodWetzer, E., Gay, J., Harlin, H., Lindblad, J., & Sladoje, N. (2020) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi45749.2020.9098424 · Cited by 13
“Augmentations were performed using [25] with a probability of 0.”
MethodDARWIN: A Highly Flexible Platform for Imaging Research in RadiologyPreprint
Chang, L., Zhuang, W., Wu, R., Feng, S., Liu, H., Yu, J., Ding, J., Wang, Z., & Zhang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00908 · Cited by 11
Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-TransformersPreprint
Henkel, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03786 · Cited by 23
“For training we resize all image to a square size and apply shift, scale, rotate and cutout augmentation using albumentations [1].”
Fully convolutional Siamese neural networks for buildings damage assessment from satellite imagesPreprint
Khvedchenya, E., & Gabruseva, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00508 · Cited by 11
“For augmenting images, we used an open-source library Albumentations Buslaev et al. [2020].”
Self-citationSelf-Supervised Learning for Fine-Grained Image ClassificationPreprint
Breiki, F. A., Ridzuan, M., & Grandhe, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.13973 · Cited by 13
“Coarse dropout was the second image-level augmentation that was applied from the albumentations library [3].”
MethodCherryChèvre: A fine-grained dataset for goat detection in natural environments
Vayssade, J.-A., Arquet, R., Troupe, W., & Bonneau, M. (2023) · Scientific Data · doi:10.1038/s41597-023-02555-8 · Cited by 11
“This can also be implemented as a data augmentation technique 26 .”
MethodMarzola, F., Lochner, P., Naldi, A., Lemor, R. M., Stögbauer, J., & Meiburger, K. M. (2023) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2023.05.011 · Cited by 10
Data augmentation and data mining towards microstructure and property relationship for composites
Guo, Z., Liu, X., Pan, Z., Zhou, Y., Zhong, Z., & Yan, Z. (2023) · Engineering Computations · doi:10.1108/ec-10-2022-0639 · Cited by 10
The Effect of Data Augmentation in Deep Learning with Drone Object Detection
Alin, A. Y., Kusrini, K., & Yuana, K. A. (2023) · IJCCS (Indonesian Journal of Computing and Cybernetics Systems) · doi:10.22146/ijccs.84785 · Cited by 14
“The implementation of this detailed augmentation pipeline can be expressed concisely in a code snippet [14].”
BackgroundExplainable Connectionist-Temporal-Classification-Based Scene Text Recognition
Buoy, R., Iwamura, M., Srun, S., & Kise, K. (2023) · Journal of Imaging · doi:10.3390/jimaging9110248 · Cited by 12
“In addition, because the synthetically generated training images were already augmented during generation, additional data augmentation, such as [54,55], may affect the recognition accuracy negatively [45].”
BackgroundFeldman, M. J., Park, J., Miller, N. D., Wakholi, C., Greene, K., Abbasi, A., Rippner, D. A., Navarre, D. A., Carley, C. A. S., Shannon, L. M., et al. (2024) · The Plant Phenome Journal · doi:10.1002/ppj2.20099 · Cited by 10
“In this study, a Python (version 3.9) library, Albumentations (Buslaev et al., 2020), was used to perform random image augmentation on the hollow-heart potato images.”
InfluentialAn in-depth analysis of data reduction methods for sustainable deep learning
Perera-Lago, J., Toscano-Durán, V., Paluzo-Hidalgo, E., González-Díaz, R., Gutiérrez-Naranjo, M. Á., & Rucco, M. (2024) · Open Research Europe · doi:10.12688/openreseurope.17554.1 · Cited by 17
“In addition, YOLOv5 uses several augmen-tations such as Mosaic, copy-paste, random affine, MixUp, HSV augmentation, random horizontal flip, as well as other augmentations from the albumentations package [8].”
MethodGietz, H., Sharma, J., & Tyagi, M. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3408140 · Cited by 11
“Concerns about the model’s generalizability, particularly regarding the consistent location of sand in most training and validation datasets, led to the implementation of data flipping techniques, a common practice in ML settings [35], [36], [37], [38].”
BackgroundAE-YOLOv5 for Detection of Power Line Insulator Defects
Shen, W., Fang, M., Wang, Y., Xiao, J., Chen, H., Zhang, W., & Li, X. (2024) · IEEE Open Journal of the Computer Society · doi:10.1109/ojcs.2024.3465430 · Cited by 10
“2) takes the image I ∈ R 608 × 608 × 3 and several data augmentation tricks are adopted, including HSV enhancement, Mosaic [27], CutMix [28], Cutout [29], Mixup [30], RandomPerspective, and Albumentions [31], etc. (2) Backbone (the light green box in Fig.”
MethodRevisiting the Domain Gap Issue in Non-cooperative Spacecraft Pose Tracking
Liu, K., & Yu, Y. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00680 · Cited by 19
“Data augmentation excluding Style Augmentation is implemented by Albumentations[26].”
MethodBoyd, C., Brown, G. C., Kleinig, T. J., Mayer, W., Dawson, J. A., Jenkinson, M., & Bezak, E. (2024) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.14542 · Cited by 10
“26 Albumentations 27 was used for data augmentation, where mentioned.”
PACT-3D, a deep learning algorithm for pneumoperitoneum detection in abdominal CT scans
Chiu, I.-M., Huang, T., Ouyang, D., Lin, W., Pan, Y., Lu, C.-Y., & Kuo, K. (2024) · Nature Communications · doi:10.1038/s41467-024-54043-1 · Cited by 10
Baek, J.-W., Kim, J.-I., & Kim, C.-B. (2024) · PLoS ONE · doi:10.1371/journal.pone.0313323 · Cited by 15
Moreira, G., dos Santos, F. N., & Cunha, M. (2024) · Smart Agricultural Technology · doi:10.1016/j.atech.2024.100690 · Cited by 10
Early detection of marine bioinvasion by sun corals using YOLOv8
Luz, A. C. N., Barroso, V. R., Batista, D., Lessa, A. A., Coutinho, R., & Xavier, F. C. (2025) · Intelligent Marine Technology and Systems · doi:10.1007/s44295-024-00052-1 · Cited by 10
“To ensure the best performance of the CNN model, a large amount of data is required, so the initial set of images was augmented using the Augmentor (Bloice et al. 2017) and the Albumentations (Buslaev et al. 2020) libraries, both developed in the Python language (https:// www. python. org/ doc/).”
Liu, H., Ren, X., Gan, Y., Chen, Y., & Lin, P. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3530141 · Cited by 12
Localization and detection of deepfake videos based on self-blending method
Xu, J., Liu, X., Lin, W., Shang, W., & Wang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-88523-1 · Cited by 16
Diabetic Foot Ulcer Grand Challenge 2024: Overview and Baseline Methods
Brüngel, R., Kendrick, C., Cassidy, B., Bracke, B., Friedrich, C. M., Reeves, N. D., Pappachan, J. M., & Yap, M. H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-80871-5_10 · Cited by 13
Oshino, T., Enda, K., Shimizu, H., Sato, M., Nishida, M., Kato, F., Oda, Y., Hosoda, M., Kudo, K., Iwasaki, N., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-90099-9 · Cited by 10
“During training, image augmentation was applied as follows: random resizing/cropping, horizontal flipping, noise addition, and colour arrangement 34 , to mitigate overfitting and sample imbalances.”
Attention-Enhanced Lightweight Architecture with Hybrid Loss for Colposcopic Image Segmentation
Chatterjee, P., Siddiqui, S., Kareem, R. S. A., & Rao, S. (2025) · Cancers · doi:10.3390/cancers17050781 · Cited by 10
Cho, S. Y., Kim, Y., Park, S., Paik, J. H., Chin, H. J., Park, J. H., Lee, J. P., Kim, Y., Park, S.-H., Lee, H.-C., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-09031-w · Cited by 10
Laroca, R., Estevam, V., Moreira, G. J. P., Minetto, R., & Menotti, D. (2025) · IET Intelligent Transport Systems · doi:10.1049/itr2.70086 · Cited by 17
Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation
Laroca, R., Santos, M. D., & Menotti, D. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227421 · Cited by 10
“To enhance variability, these patches were augmented using the Albumen-tations library [37], applying transformations such as blurring, pixel dropout, noise addition, and adjustments to brightness, contrast and gamma.”
Fu, J., Dai, D., Huang, S., Xie, J., He, Y., Dong, C., Xia, K., Zheng, J., & Chen, S. (2025) · Current Research in Food Science · doi:10.1016/j.crfs.2025.101269 · Cited by 10
“2 ] , β ∈ [(cid:0) 10 , 10 ] ) (Buslaev et al., 2020; Xu et al., 2023).”
Improving small object detection in open water maritime monitoring under low-shot learning
Liao, W., Ma, Q., Wang, H., & Li, H. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.123307 · Cited by 10
Blanch, X., Grundmann, J., Hedel, R., & Eltner, A. (2026) · Hydrology and earth system sciences · doi:10.5194/hess-30-797-2026 · Cited by 15
Detecting subsurface drainage pipes using a fully convolutional network with optical images
Song, H., Woo, D. K., & Yan, Q. (2021) · Agricultural Water Management · doi:10.1016/j.agwat.2021.106791 · Cited by 10
Spectral decoupling for training transferable neural networks in medical imaging
Pohjonen, J., Stürenberg, C., Rannikko, A. S., Mirtti, T. K., & Pitkänen, E. (2022) · iScience · doi:10.1016/j.isci.2022.103767 · Cited by 12
The MeVer DeepFake Detection Service: Lessons Learnt from Developing and Deploying in the Wild
Baxevanakis, S., Kordopatis-Zilos, G., Galopoulos, P., Apostolidis, L., Levacher, K., Schlicht, I. B., Teyssou, D., Kompatsiaris, I. Y., & Papadopoulos, S. (2022) · doi:10.1145/3512732.3533587 · Cited by 12
“the Albumentations library [4]: Geometric augmentations (Rotate, HorizontalFlip), Color augmentations (ColorJitter, ToGray), Blurring (MotionBlur, GaussianBlur), Image Corruption (ISONoise, CoarseDropout), External Effects (RandomSunFlare, RandomRain).”
BackgroundSBDF-Net: A versatile dual-branch fusion network for medical image segmentation
Wang, J., Tian, S., Yu, L., Wang, Y., Wang, F., & Zhou, Z. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103928 · Cited by 10
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.