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 901–1,000 of 1,006
Saadi, S. B., Moreno‐Rabié, C., WYNGAERT, T. V. D., & Jacobs, R. (2022) · Bone Reports · doi:10.1016/j.bonr.2022.101632 · Cited by 10
“Due to the limited dataset, data augmentation was performed using an open source Python library, Albumentations augmentation library (Buslaev et al., 2020).”
MethodThakur, M., & Umapathy, S. (2022) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-022-01196-2 · Cited by 10
Enhanced Plastic Recycling using RGB+Depth Fusion with MassFaster and MassMask R-CNN
Romero, D. J. D., Zaplana, I., den Eynde, S. V., Sterkens, W., Goedemé, T., & Peeters, J. R. (2022) · International Conference on Transdisciplinary AI (TransAI) · doi:10.1109/transai54797.2022.00010 · Cited by 10
“During the retraining, Random Sized BBox Safe Crop, Shift Scale Rotate, Random Brightness Contrast, Hue Saturation Value, Random Gamma, Gauss Noise, Gaussian Blur, Horizontal Flip, and Vertical Flip are applied as data augmentation methods using the Albumentations library [24].”
MethodODOR: The ICPR2022 ODeuropa Challenge on Olfactory Object Recognition
Zinnen, M., Madhu, P., Kosti, R., Bell, P. R. F., Maier, A., & Christlein, V. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956542 · Cited by 15
“For training, the team applied mild data augmentation as given by the aug tfms function of the albumentations [8] library.”
MethodGC-Net: Global and Class Attention Blocks for Automated Glaucoma Classification
Tian, H., Lu, S., Sun, Y., & Li, H. (2022) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea54703.2022.10005946 · Cited by 10
“For the data augmentation, we use the Compose and OneOf method of the Albumentation library [17], which reduces overfitting and improves the performance of classifiers.”
MethodBrüngel, R., Koitka, S., & Friedrich, C. M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26354-5_6 · Cited by 10
Automated Visual Identification of Foliage Chlorosis in Lettuce Grown in Aquaponic Systems
Abbasi, R., Martínez, P., & Ahmad, R. (2023) · Agriculture · doi:10.3390/agriculture13030615 · Cited by 12
Adversarial Domain Generalization for Surveillance Face Anti-Spoofing
Liu, Y., Xu, Y., Zou, Z., Wang, Z., Zhang, B., Wu, L., Guo, Z., & He, Z. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00676 · Cited by 10
“The data augmentation methods [3] include Coarse-Dropout, Random Flip, RandomRotate, RandomCrop, Mo-tionBlur, GaussianBlur, Sharpen, Downsampling, Random-lyErase, RandomFog, Posterize, etc.”
Automatic lameness detection in dairy cows based on machine vision
Jia, Z., Yang, X., Wang, Z., Yu, R., & Wang, R. (2023) · International journal of agricultural and biological engineering · doi:10.25165/j.ijabe.20231603.8097 · Cited by 14
Ding, Q., Shao, Z., Huang, X., Feng, X., Altan, O., & Hu, B. (2023) · GIScience & Remote Sensing · doi:10.1080/15481603.2023.2257980 · Cited by 10
“The unsupervised module employs several perturbation methods based on Albumentations library (Buslaev et al. 2020), including vertical flip, horizontal flip, random rotate 90°, transpose, and random grid shuffle, as shown in Figure 5.”
MethodDALib: A Curated Repository of Libraries for Data Augmentation in Computer Vision
Amarù, S., Marelli, D., Ciocca, G., & Schettini, R. (2023) · Journal of Imaging · doi:10.3390/jimaging9100232 · Cited by 12
“Albumentations [21] albumentations-team/albumentations (https://github.com/albumentations-team/albumentations) 2023 AugLy [22] facebookresearch/AugLy (https://github.com/facebookresearch/AugLy) 2023 Augmentor [23] mdbloice/Augmentor (https://github.com/mdbloice/Augmentor) 2023 Augraphy [24]…”
BackgroundCharnpinyo, N., Suthicharoenpanich, K., Onthuam, K., Engphaiboon, S., Chaichaowarat, R., Suebthawinkul, C., & Siricharoen, P. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340767 · Cited by 10
“In this study, the augmentations were applied using Al-bumentations library [9], which efficiently various image transformation techniques.”
MethodSimultaneous, vision-based fish instance segmentation, species classification and size regression
Climent-Pérez, P., Galán-Cuenca, A., García-D’Urso, N., Saval-Calvo, M., Azorín-López, J., & Fuster-Guilló, A. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1770 · Cited by 14
Zhang, X., Guo, J., Yoo, P., Matsuo, Y., & Iwasawa, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448510 · Cited by 10
Enhancing Detection of Remotely-Sensed Floating Objects via Data Augmentation for Maritime SAR
Mahmoud, H., Kurniawan, I. F., Aneiba, A., & Asyhari, A. T. (2024) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-024-01869-3 · Cited by 11
“The image data are modified using the Albumentation library (Buslaev et al., 2020).”
Multi-feature fusion based face forgery detection with local and global characteristics
Ding, Y., Bu, F., Zhai, H., Hou, Z., & Wang, Y. (2024) · PLoS ONE · doi:10.1371/journal.pone.0311720 · Cited by 12
Semi-automatic Manga Colorization Using Conditional Adversarial Networks
Golyadkin, M., & Makarov, I. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72610-2_17 · Cited by 10
“Image augmentations are performed with the Albumentations [2].”
BackgroundElanwar, R., Qin, W., Betke, M., & Wijaya, D. T. (2021) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-021-00382-4 · Cited by 11
Detecting aerial objects: drones, birds, and helicopters
Mediavilla, C., Nans, L., Marez, D., & Parameswaran, S. (2021) · Artificial Intelligence and Machine Learning in Defense Applications · doi:10.1117/12.2600068 · Cited by 10
Sadaf, F., Raju, S. M. T. U., & Muntakim, A. (2021) · International Conference on Electrical & Electronic Engineering (ICEEE) · doi:10.1109/iceee54059.2021.9718890 · Cited by 10
Deep Learning Pipeline for Chromosome Segmentation
Pijackova, K., Götthans, T., & Gotthans, J. (2022) · International Conference Radioelektronika · doi:10.1109/radioelektronika54537.2022.9764950 · Cited by 11
Accurate Crack Detection Based on Distributed Deep Learning for IoT Environment
Kim, Y., Yi, S., Ahn, H., & Hong, C.-H. (2023) · Sensors · doi:10.3390/s23020858 · Cited by 11
Remote Sensing Data Preparation for Recognition and Classification of Building Roofs
Hristov, E., Petrova‐Antonova, D., Petrov, A., Borukova, M., & Shirinyan, E. (2023) · Data · doi:10.3390/data8050080 · Cited by 10
Underwater Object Detection With Mixed Attention Mechanism And Multi-Enhancement Strategy
Chen, W., & Fan, B. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9326737 · Cited by 11
Zioulis, N., Álvarez, F., Zarpalas, D., & Daras, P. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104160 · Cited by 10
Burduja, M., Ionescu, R. T., & Verga, N. I. (2020) · Sensors · doi:10.3390/s20195611 · Cited by 157
“Using the Albumentations library [51], the transformations that we chosen for data augmentation are: horizontal flipping, shifting, rotation, scaling and brightness adjustment.”
Masuda, M., Soufi, M., Otake, Y., Uemura, K., Kono, S., Takashima, K., Hamada, H., Gu, Y., Takao, M., Okada, S., et al. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03087-1 · Cited by 9
“Data augmentation was applied during training and inference using Albumentations (ver.1.1.0) [26].”
MethodInfluentialDRI-Net: a model for insulator defect detection on transmission lines in rainy backgrounds
Ji, C., Gao, M., Zhou, S., Liu, J., Zhu, Y., & Huang, X. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01461-5 · Cited by 9
Sun, J., Li, Y., Wu, X., Tang, C., Wang, S., & Zhang, Y. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104151 · Cited by 11
Boiko, D. A., Arkhipova, D. M., & Ananikov, V. P. (2024) · Small · doi:10.1002/smll.202403423 · Cited by 9
STar-DETR: A Lightweight Real-Time Detection Transformer for Space Targets in Optical Sensor Systems
Xiao, Y., Guo, Y., Pang, Q., Yang, X., Zhao, Z., & Yin, X. G. (2025) · Sensors · doi:10.3390/s25041146 · Cited by 13
Robust automatic crater detection at all latitudes on Mars with deep-learning
Martinez, L., Andrieu, F., Schmidt, F., Talbot, H., & Bentley, M. (2025) · Planetary and Space Science · doi:10.1016/j.pss.2025.106053 · Cited by 11
A Deep Learning Segmentation Model for Detection of Active Proliferative Diabetic Retinopathy
Dinesen, S., Schou, M. G., Hedegaard, C. V., Subhi, Y., Savarimuthu, T. R., Pető, T., Andersen, J., & Grauslund, J. (2025) · Ophthalmology and Therapy · doi:10.1007/s40123-025-01127-w · Cited by 10
“Images were augmented with the albu-mentations library [26] using different spatial and pixel-level transforms.”
Robust and efficient single-CNN-based spacecraft relative pose estimation from monocular images
Bechini, M., & Lavagna, M. R. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.04.016 · Cited by 13
Safdar, M., Wood, G., Zimmermann, M., Lamouche, G., Wanjara, P., & Zhao, Y. F. (2025) · Virtual and Physical Prototyping · doi:10.1080/17452759.2025.2515240 · Cited by 11
Suppa, A. R., Aliberti, A., Bottero, M., & Corrado, V. (2025) · Building Simulation · doi:10.1007/s12273-025-1301-3 · Cited by 13
“To each batch, we add blur functions using the Albumentations library (Buslaev et al. 2020), expecting that training with blurred images will lead to better predictions on the dataset where tall and wide buildings frequently contain noise at upper and lateral extents.”
Boité, H. L., Bonnin, S., Gallardo, M., Lamard, M., Couturier, A., & Quellec, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-15712-3 · Cited by 10
“…of 0 to 90°, random 10% cropping, random elastic deformation and brightness and contrast modifications, all using the albumentations python library 42 , a binary cross-entropy loss, an Adam optimizer, a weight decay of 10 − 4 , a batch size of 4, and an initial learning rate of 10 − 3 , with a…”
Vanhaeverbeke, J., Verstockt, S., & van Hoecke, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-16276-y · Cited by 10
“To increase data variation and regularization during training, runtime image augmentations 27 are employed.”
Low‐complexity real‐time detection Transformer for identifying bridge vehicle loads
Chang, L., Tang, Q., Xin, J., Jiang, Y., Zhang, H., Li, Z., Zhou, Y., & Zhou, J. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.70061 · Cited by 9
“…unseen conditions while eliminating data leakage risks, corresponding weather-impacted scenes were synthesized using the Albumentations library (Buslaev et al., 2020) on an independent overcast test sub-set, where such conditions deliberately excluded during model training for unbiased…”
Effects of segmentation errors on downstream-analysis in highly-multiplexed tissue imaging
Bruhns, M., Schleicher, J. T., Wirth, M., Zago, M., Babaei, S., & Claassen, M. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013350 · Cited by 15
“Specifically, we use the Affine function from the Albumentations library [20], which applies translation, rotation, scaling, and shearing to each cell mask.”
Gautam, S., Riegler, M. A., & Halvorsen, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08009-7_6 · Cited by 28
A YOLO-based substation defect detection model with enhanced feature extraction and fusion
Cheng, W., Liu, Z., Du, J., Yang, W., & Wang, T. (2025) · Electric Power Systems Research · doi:10.1016/j.epsr.2025.112354 · Cited by 9
WAAM-ViD: towards universal vision-based monitoring for wire arc additive manufacturing
Kim, K. W., Kamerkar, A., Chiu, T.-E., Abdi, I., Qin, J., Suder, W., & Asif, S. (2025) · Frontiers in Manufacturing Technology · doi:10.3389/fmtec.2025.1676365 · Cited by 15
Yuan, W., Yao, B., Tan, S., You, F., & He, Q. (2025) · npj Computational Materials · doi:10.1038/s41524-025-01800-5 · Cited by 12
“While conventional data augmentation methods ( e.g ., geometric or photometric transforms via Albumentations 45 ) are widely used in computer vision, they areofteninadequateformodelingthephysics-drivenartifactsuniquetoEM imaging.”
Oh, S. J., Shin, J.-I., Kim, E. N., Widiastini, A., Hong, Y., Sohn, I., Jin, K. N., Lim, J. S., Kim, J. S., Choi, H.-J., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-22167-z · Cited by 9
Islam, S., Wishart, G. C., Walls, J., Hall, P. N., de Herrera, A. G. S., Gan, J. Q., & Raza, H. (2026) · Scientific Reports · doi:10.1038/s41598-025-26392-4 · Cited by 14
“In our pipeline, we used the following augmentations from the popular and powerful Pytorch augmentation library Albumentations 32 : Transpose, Flip, Rotate, RandomBrightness, RandomContrast, MotionBlur, MedianBlur, GaussianBlur, GaussNoise, OpticalDistortion, GridDistortion, ElasticTransform, CLAHE, HueSaturationValue…”
InfluentialZhang, Y., Konz, N., Kramer, K., & Mazurowski, M. A. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00505 · Cited by 17
Toda, Y., Tameshige, T., Tomiyama, M., Kinoshita, T., & Shimizu, K. K. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.715309 · Cited by 9
“The image transformation and the converting bounding-box coordinates were performed using Albumentations (Buslaev et al., 2020), an image augmentation library.”
MethodAutomatic Snake Classification using Deep Learning Algorithm.
Kalinathan, L., Balasundaram, P., Ganesh, P., Bathala, S. S., & Mukesh, R. K. (2021) · CLEF (Working Notes) · Cited by 9
Schilling, M. P., Schmelzer, S., Gómez, J. E. U., Popova, A. A., Levkin, P. A., & Reischl, M. (2021) · IEEE Access · doi:10.1109/access.2021.3135709 · Cited by 10
“We implement the UNet in PyTorch Lightning [31] and use data augmentation such as image flipping, shifting, rotating, rescaling, cropping, Gaussian noise superposition, contrast adjustment, and adaptation of brightness provided by Albumentations [32].”
MethodFAPNET: Feature Fusion with Adaptive Patch for Flood-Water Detection and Monitoring
Islam, M. S., Sun, X., Wang, Z., & Cheng, I. (2022) · Sensors · doi:10.3390/s22218245 · Cited by 10
CSN: Component supervised network for few-shot classification
Xu, R., Shao, S., Xing, L., Wei, Y., Liu, W., Liu, B., & Wang, Y. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106640 · Cited by 9
Ferlin, M. A., Klawikowska, Z., Grochowski, M., Grzywińska, M., & Szurowska, E. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120655 · Cited by 10
Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation
Liu, X., Ono, K., & Bise, R. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230495 · Cited by 11
“Simple data augmentation methods, which do not require searching for additional parameters, basically give perturbations ( e.g. , GaussianBlur, GridDropout [4]) to the entire region of an original image as augmented images.”
InfluentialDeep Learning Approach for the Localization and Analysis of Surface Plasmon Scattering
Lee, J., Moon, G., Ka, S., Toh, K., & Kim, D. (2023) · Sensors · doi:10.3390/s23198100 · Cited by 9
Jung, G., Kim, S., Lee, J.-H., & Yoo, S. (2023) · Skin Research and Technology · doi:10.1111/srt.13486 · Cited by 9
AngioMoCo: Learning-Based Motion Correction in Cerebral Digital Subtraction Angiography
Su, R., van der Sluijs, M., Cornelissen, S. A., van Zwam, W. H., van der Lugt, A., Niessen, W. J., Ruijters, D., van Walsum, T., & Dalca, A. V. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43990-2_72 · Cited by 11
Multi-Layer Scene Representation from Composed Focal Stacks
Ishikawa, R., Saitô, H., Kalkofen, D., & Mori, S. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2023.3320248 · Cited by 9
“We used the Albumentations library [7], which receives [ 0 , 1 ] values as intensities to add ISO noises and motion blurs to images.”
MethodAutomatic Detection and Mapping of Dolines Using U-Net Model from Orthophoto Images
Polat, A., Keskin, İ., & Polat, Ö. (2023) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi12110456 · Cited by 9
Image classification for historical documents: a study on Chinese local gazetteers
Chen, J.-A., Hou, J.-C., Tsai, R. T., Liao, H.-M., Chen, S.-P., & Chang, M. (2023) · Digital Scholarship in the Humanities · doi:10.1093/llc/fqad065 · Cited by 10
“This augmentation is often achieved by applying random transformations like rotation, flipping, and cropping to the existing data (Bloice, Roth, and Holzinger 2019; Buslaev et al. 2020).”
MethodVerboom, S. D., Caballo, M., Peters, J., Gommers, J. J. J., van den Oever, D., Broeders, M. J. M., Teuwen, J., & Sechopoulos, I. (2023) · Journal of medical imaging · doi:10.1117/1.jmi.11.1.014001 · Cited by 9
Saliency and Power Aware Contrast Enhancement for Low OLED Power Consumption
Nugroho, K. A., & Ruan, S.-J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3350145 · Cited by 10
“Random cropping of 450 × 450, brightness contrast, inversion, and horizontal flipping are used for image augmentation [103].”
MethodDeep learning application for abdominal organs segmentation on 0.35 T MR-Linac images
Zhou, Y., Lalande, A., Chevalier, C., Baude, J., Aubignac, L., Boudet, J., & Bessières, I. (2024) · Frontiers in Oncology · doi:10.3389/fonc.2023.1285924 · Cited by 9
Image Segmentation using Deep Neural Network for the Autonomous Aerial Refueling Mission
Mwaffo, V., Costello, D. H., & Miller, D. (2024) · AIAA SciTech Forum · doi:10.2514/6.2024-2767 · Cited by 9
Wang, Y., Dan, R., Luo, S., Sun, L., Wu, Q., Li, Y., Chen, X.-D., Yan, K., Ye, X., & Yu, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123496 · Cited by 10
Detecting bone lesions in X-ray under diverse acquisition conditions
Zimbalist, T., Rosen, R., Peri-Hanania, K., Caspi, Y., Rinott, B., Zeltser-Dekel, C., Bercovich, E., Eldar, Y. C., & Bagon, S. (2024) · Journal of medical imaging · doi:10.1117/1.jmi.11.2.024502 · Cited by 9
“Both pixel-level and spatial-level augmentations were applied using Albumentations library [20].”
MethodSaunders-Shultz, P., Lopez, T. M., Dietterich, H. R., & Girona, T. (2024) · Frontiers in Earth Science · doi:10.3389/feart.2024.1345104 · Cited by 9
Slotman, D. J., Bartels, L. W., Nijholt, I. M., Huirne, J. A. F., MOONEN, C. T. W., & Boomsma, M. F. (2024) · European Journal of Radiology · doi:10.1016/j.ejrad.2024.111602 · Cited by 11
Rathod, K., Choudhary, A. K., Jansche, A., Ketzer‐Raichle, G., Bernthaler, T., & Schneider, G. (2024) · Materials Characterization · doi:10.1016/j.matchar.2024.114379 · Cited by 9
Mapping decadal land cover dynamics in Sicily’s coastal regions
Scala, P., Toimil, A., Álvarez-Cuesta, M., Manno, G., & Ciraolo, G. (2024) · Scientific Reports · doi:10.1038/s41598-024-73085-5 · Cited by 9
“To avoid overfitting, the original dataset of 134 images was augmented using data augmentation techniques (e.g., cropping, rotation, brightness and contrast adjustment) with the Python Albumentations library 61 .”
MethodAdaptive Curriculum Query Strategy for Active Learning in Medical Image Classification
Ma, S., Du, H., Curran, K. M., Lawlor, A., & Dong, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72120-5_5 · Cited by 17
Cannabis Seed Variant Detection Using Faster R-CNN
Sarker, T. T., Islam, T., & Ahmed, K. R. (2024) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs60874.2024.10716962 · Cited by 9
“We use Albumentations [24] image augmentation library to apply geometric transformations, color transformations, and blur operations on training images.”
MethodDeveloping AI Smart Sprayer for Punch-Hole Herbicide Application in Plasticulture Production System
Furlanetto, R. H., Buzanini, A. C., Schumann, A. W., & Boyd, N. S. (2024) · AgriEngineering · doi:10.3390/agriengineering7010002 · Cited by 9
Zhong, M., Li, Y., & Gao, Y. (2025) · Agronomy · doi:10.3390/agronomy15010187 · Cited by 9
Benchmark for Generic Product Detection: A Low Data Baseline for Dense Object Detection
Varadarajan, S., Kant, S., & Srivastava, M. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-50347-5_3 · Cited by 9
“We apply standard object detection augmentations from (Buslaev et al., 2018).”
MethodDetection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery
Dadsetan, S., Rose, G., Hovakimyan, N., & Hobbs, J. A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i17.17730 · Cited by 10
“Data Augmentations: During training we perform data augmentation such as vertical/horizontal flipping, shifting, rotation, and padding using the Albumentations package (Buslaev et al. 2020).”
MethodKorra, S., Mamidi, R., Soora, N. R., Kumar, K. V., & Kumar, N. C. S. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7218 · Cited by 13
SAU-NET: Scale Aware Polyp Segmentation using Encoder-Decoder Network
Gautam, A., Das, S., Sharma, P., Maji, P., & Balabantaray, B. K. (2022) · IEEE Region 10 Symposium (TENSYMP) · doi:10.1109/tensymp54529.2022.9864338 · Cited by 9
“To handle this, we have used extensive offline augmentation using Albumentations [19] library.”
MethodDefective Surface Detection based on Improved Faster R-CNN
Duan, H. M., Huang, J., Liu, W., & Shu, F. (2022) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit48603.2022.10002822 · Cited by 11
“To augment 1800 images, Albumentations, an image enhancement pipeline for deep learning designed by Buslaev et al. [14], is applied to the dataset.”
MethodFast and Efficient Model for Real-Time Tiger Detection In The Wild
Kupyn, O., & Pranchuk, D. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00041 · Cited by 9
“All of the listed transforms were taken from Albumentations opensource library [4].”
BackgroundDEEP SEMANTIC SEGMENTATION FOR THE OFF-ROAD AUTONOMOUS DRIVING
Sgibnev, I. V., Sorokin, A., Vishnyakov, B. V., & Vizilter, Y. V. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-617-2020 · Cited by 9
Artificial Intelligence based identification of Total Knee Arthroplasty Implants
Ghose, S., Datta, S., Batta, V., Malathy, C., & Gayathri, M. K. (2020) · International Conference on Intelligent Sustainable Systems (ICISS) · doi:10.1109/iciss49785.2020.9315956 · Cited by 9
“For this study, a python library called Albumenations [26] was used to perform data augmentation so that we have a control over the number of original images used for our training pipeline by setting probabilities and magnitudes for each parameter.”
MethodRobust and Efficient Computation of Retinal Fractal Dimension Through Deep Approximation
Engelmann, J., Villaplana-Velasco, A., Storkey, A., & Bernabéu, M. O. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16525-2_9 · Cited by 9
What's wrong with this video? Comparing Explainers for Deepfake DetectionPreprint
Pino, S., Carman, M., & Bestagini, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.05902 · Cited by 14
“[5]: we use Pytorch [27] as deep learning framework, we perform random augmentations on the input (downscaling, horizontal flipping, brightness and colour tuning, noise and JPEG compression) with Albumentation [7], and we use Adam [17] optimizer with β1 = 0.”
MethodScaling Ensemble Distribution Distillation to Many Classes with Proxy TargetsPreprint
Ryabinin, M., Malinin, A., & Gales, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.06987 · Cited by 11
“For data augmentations, we use a combination of random resized crops and horizontal flips implemented in the Albumentations library [29].”
MethodDeep learning based histological classification of adnex tumors
Jansen, P., Arrastia, J. L., Baguer, D. O., Schmidt, M., Landsberg, J., Wenzel, J., Emberger, M., Schadendorf, D., Hadaschik, E., Maass, P., et al. (2024) · European Journal of Cancer · doi:10.1016/j.ejca.2023.113431 · Cited by 8
Müller, P., Meissen, F., Kaissis, G., & Rueckert, D. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3435015 · Cited by 8
“During training, we augmented the data by applying random color jitter and random Gaussian blurring, each with a probability of 50%, using the Albumentations library [46].”
MethodChestnut Burr Segmentation for Yield Estimation Using UAV-Based Imagery and Deep Learning
Carneiro, G. A., Santos, J. F. D. L., Sousa, J. J., Cunha, A. M. T. D. S., & Pádua, L. (2024) · Drones · doi:10.3390/drones8100541 · Cited by 8
Dao, Y., Liang, B., Hao, L. F., Feng, S., Wei, S., Dai, W., & Gu, F. (2024) · Astronomy and Computing · doi:10.1016/j.ascom.2024.100881 · Cited by 8
Kozhekin, M. V., Александрович, Г. М., Komyshev, E. G., Zavyalov, Z. A., & Afonnikov, D. A. (2025) · Journal of Imaging · doi:10.3390/jimaging11010028 · Cited by 8
Sriwatana, K., Puttanawarut, C., Suwan, Y., & Achakulvisut, T. (2025) · Translational Vision Science & Technology · doi:10.1167/tvst.14.1.22 · Cited by 8
Wagner, L., Costello, D. H., & Mwaffo, V. (2025) · AIAA SciTech Forum · doi:10.2514/6.2025-1930 · Cited by 8
Chen, F., Liu, H., Zeng, Z., & Tan, X. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3555536 · Cited by 8
“The data augmentation methods and parameters (Params) initialization in training are according to the default setup of the Albumentations [38].”
Attention-enhanced separable residual with dilation net for medical image segmentation
Xiao, L., Liu, Y., & Fan, C. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130434 · Cited by 10
Kasamsumran, N., Ittichaiwong, P., Chinudomporn, C., Veerakanjana, K., Karoopongse, E., & Pora, W. (2025) · IEEE Access · doi:10.1109/access.2025.3569767 · Cited by 11
Tsiporenko, I., Chizhov, P., & Fishman, D. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91721-9_14 · Cited by 11
Elsherbiny, O., Zhou, L., He, Y., & Qiu, Z. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128583 · Cited by 8
Kim, I.-S., Yang, S. J., Choi, Y., Kwon, H.-J., Lee, C., & Park, W. (2025) · Forensic Science International · doi:10.1016/j.forsciint.2025.112531 · Cited by 8
Wang, Y., Zhang, S., Xu, J., Cheng, Z., & Du, G. (2025) · Symmetry · doi:10.3390/sym17071116 · 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.