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 601–700 of 1,006
GPR Data Augmentation Methods by Incorporating Domain Knowledge
Yue, G., Liu, C., Li, Y., Du, Y., & Guo, S. (2022) · Applied Sciences · doi:10.3390/app122110896 · Cited by 18
“Zong et al. used a computer vision tool, Albumentations [29], to augment the collected GPR data, involving a combination of blurring, cropping, rotation, mirror flip, etc. [30].”
MethodSilva, C. N. S., Dainys, J., Simmons, S., Vienožinskis, V., & Audzijonytė, A. (2022) · Sustainability · doi:10.3390/su142114324 · Cited by 18
Chen, J., Yang, Y., Luo, B., Wen, Y., Chen, Q., Ma, R., Huang, Z., Zhu, H., Li, Y., Chen, Y., et al. (2022) · Human Pathology · doi:10.1016/j.humpath.2022.11.007 · Cited by 18
Scale–Relation Joint Decoupling Network for Remote Sensing Image Semantic Segmentation
Nie, J., Zheng, C., Wang, C., Zuo, Z., Lv, X., Yu, S., & Wei, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3219585 · Cited by 19
“In addition, we use the albumentations library [44] for data augmentation and normalize all the training images to [0.”
MethodRoad Rutting Detection using Deep Learning on Images
Saha, P. K., Arya, D., Kumar, A., Maeda, H., & Sekimoto, Y. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020458 · Cited by 17
“Further, image augmentation techniques using albumentations [45] were explored with the objective to improve the detection accuracy of the YOLOv4 model.”
MethodNuclei probability and centroid map network for nuclei instance segmentation in histology images
Rashid, S. N., & Fraz, M. M. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08503-2 · Cited by 21
“All these data augmentations were carried out using Albumentations [58] library.”
MethodSobhy, A., Helmy, M., Khalil, M., Elmasry, S., Boules, Y., & Negied, N. K. (2023) · IEEE Access · doi:10.1109/access.2023.3267981 · Cited by 17
Gonçalves, C. D. A., Borges, A. L., Dias, V. B. L., Marques, J. V. M., Aguiar, B. G. A., Costa, C. H. N., & Silva, R. (2023) · Applied Sciences · doi:10.3390/app13148076 · Cited by 18
Multi-Configuration Analysis of DenseNet Architecture for Whole Slide Image Scoring of ER-IHC
Ahmad, W. S. H. M. W., Fauzi, M. F. A., Hasan, M. J., Rehman, Z. U., Lee, J. T. H., Khor, S. Y., Looi, L., Abas, F. S., Adam, A., Chan, E. W. L., et al. (2023) · IEEE Access · doi:10.1109/access.2023.3296848 · Cited by 18
“In this experiment, we used data augmentation from Albumentations [36] image transformations, based on vertical and horizontal flip, shifting hue, saturation and value limits, rotation and random size crop.”
MethodAn improvement of the CNN-XGboost model for pneumonia disease classification
Hedhoud, Y., Mekhaznia, T., & Amroune, M. (2023) · Polish Journal of Radiology · doi:10.5114/pjr.2023.132533 · Cited by 18
“Unlike classic augmentation approaches, which are limited to simple geometric transformations, we used the Albumentations tool, which allows image transformation operations [28].”
MethodLiu, F., Zhang, Z., & Li, S. (2023) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3332075 · Cited by 18
“The To bolster the model’s generalization capabilities, we apply extra data augmentation methods [49] including Random Erase, Sun Flare, and Style Augment on the SPEED+ dataset and implement a self-supervised domain adaption method from Wang et al. [50] on randomly selected samples from the…”
MethodSiami, M., Barszcz, T., Wodecki, J., & Zimroz, R. (2024) · Scientific Reports · doi:10.1038/s41598-024-55864-2 · Cited by 19
“In this paper, image augmentation was implemented using the open-source Albumentations package 33,68 .”
MethodPCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards
Arbash, E., Fuchs, M., Rasti, B., Lorenz, S., Ghamisi, P., & Gloaguen, R. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3380826 · Cited by 19
“Albumentations [51], a powerful image augmentation Python library, was employed to apply various transformations to both RGB images and their corresponding masks.”
MethodAnatomically aware dual-hop learning for pulmonary embolism detection in CT pulmonary angiograms
Condrea, F., Rapaka, S., Lucian Mihai, I. T. U., Sharma, P. K., Sperl, J. I., Ali, A. M., & Leordeanu, M. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108464 · Cited by 22
DefectGAN: Synthetic Data Generation for EMU Defects Detection With Limited Data
Liu, S., Ni, H., Li, C., Zou, Y., & Luo, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3386711 · Cited by 18
“For the second experiment, YOLO v5 was applied as the baseline model and compared with online image space and color space augmentation that was implemented by Albu-mentations [47].”
MethodKoriakina, N., Sladoje, N., Bašić, V., & Lindblad, J. (2024) · PLoS ONE · doi:10.1371/journal.pone.0302169 · Cited by 21
Vision-based method to identify materials transported by dump trucks
Driouache, Y., Milpied, J., & Motamedi, A. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108768 · Cited by 18
Detection and Classification of Cannabis Seeds Using RetinaNet and Faster R-CNN
Islam, T., Sarker, T. T., Ahmed, K. R., & Lakhssassi, N. (2024) · Seeds · doi:10.3390/seeds3030031 · Cited by 19
“Implementation of these augmentation techniques is facilitated using the Albumentations library [42].”
Soomro, D. B., ChengLiang, W., Ashraf, M., AlHammadi, D. A., Alsubai, S., Medaglia, C. M., Innab, N., & Umer, M. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105537 · Cited by 20
A Framework for Knowing Who is Doing What in Aerial Surveillance Videos
Yang, F., Sakti, S., Wu, Y., & Nakamura, S. (2019) · IEEE Access · doi:10.1109/access.2019.2924188 · Cited by 17
Pneumothorax Segmentation with Effective Conditioned Post-Processing in Chest X-Ray
Groza, V., & Kuzin, A. A. (2020) · doi:10.1109/isbiworkshops50223.2020.9153444 · Cited by 19
“We also used random data augmentations [12] during the training such as Random 90 degree rotations, Horizontal flips, Transpose, ShiftScaleRotate and BrightnessContrastGamma.”
MethodDCNN-based Screw Classification in Automated Disassembly Processes
Yildiz, E., & Wörgötter, F. (2020) · International Conference on Robotics, Computer Vision and Intelligent Systems (ROBOVIS) · doi:10.5220/0009979900610068 · Cited by 17
“Using the Albumentations (Buslaev et al., 2020) library applied a rotation of 360 degrees,”
MethodMeasurement of hybrid rocket solid fuel regression rate for a slab burner using deep learning
Surina, G., Georgalis, G., Aphale, S. S., Patra, A., & DesJardin, P. E. (2021) · Acta Astronautica · doi:10.1016/j.actaastro.2021.09.046 · Cited by 17
“Albumentations library [5], each training image is rotated and flipped in random directions and magnitudes.”
BackgroundArtificial Intelligence in Quantitative Ultrasound Imaging: A Survey
Zhou, B., Yang, X., Curran, W. J., & Liu, T. (2021) · Journal of Ultrasound in Medicine · doi:10.1002/jum.15819 · Cited by 22
“14 – 18 Irrelevant or partially relevant features can negatively impact model performance.”
BackgroundFine-Scale Sea Ice Segmentation for High-Resolution Satellite Imagery with Weakly-Supervised CNNs
Gonçalves, B. C., & Lynch, H. J. (2021) · Remote Sensing · doi:10.3390/rs13183562 · Cited by 17
“…variants: (1) Log-Cosh Dice loss [33], an attempt to improve the original Dice loss by smoothing out its loss function; (2) Dice Perimeter loss [36], a variation of Dice loss that uses the difference in the total perimeter of the predicted and ground truth masks as a regularization factor to…”
BackgroundTowards Rotation Invariance in Object Detection
Kalra, A., Stoppi, G., Brown, B., Agarwal, R., & Kadambi, A. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00351 · Cited by 17
“Yet somehow this “Largest Box” method is very prevalent both in academia and in large scale object detection codebases [43, 4, 45, 37, 28, 26, 5, 7, 1, 17, 6, 40].”
BackgroundDigital Peter: New Dataset, Competition and Handwriting Recognition Methods
Potanin, M., Dimitrov, D., Shonenkov, A., Bataev, V., Karachev, D. K., Novopoltsev, M., & Chertok, A. V. (2021) · doi:10.1145/3476887.3476892 · Cited by 20
“We used the Albumentations [3] package, and found the following modifications useful: – Random image rotation by 4 ◦ clockwise or counterclockwise’ – Random change of width from 95% to 105%’ – Grid distortion.”
MethodThe Evolution of Geotech - 25 Years of Innovation
Hammah, R. E., Yacoub, T. E., McQuillan, A., & Curran, J. H. (2021) · CRC Press eBooks · doi:10.1201/9781003188339 · Cited by 18
Fully automatic segmentation and monitoring of choriocapillaris flow voids in OCTA images
López-Varela, E., de Moura, J., Novo, J., Fernández‐Vigo, J. I., Moreno-Morillo, F. J., & Ortega, M. (2023) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2022.102172 · Cited by 17
SuperpixelGridMasks Data Augmentation: Application to Precision Health and Other Real-world Data
Hammoudi, K., Cabani, A., Slika, B., Benhabiles, H., Dornaika, F., & Melkemi, M. (2022) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-022-00122-1 · Cited by 14
“Frequent methods can be divided into three categories: (i) the pixel-level transforms [5] (e.g., colorimetry-based); (ii) the spatial-level transforms [5] (e.g., geometry-based); and (iii) the information dropping and fusing [6] (e.g., mask-based).”
BackgroundMethodGlottisNetV2: Temporal Glottal Midline Detection Using Deep Convolutional Neural Networks
Kruse, E., Döllinger, M., Schützenberger, A., & Kist, A. M. (2023) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2023.3237859 · Cited by 18
Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-CasePreprint
Nesteruk, S., Shadrin, D., & Pukalchik, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.12295 · Cited by 20
“For standard augmentation we use the following methods from Albumentations package [3]: HorizontalFlip , VerticalFlip , ShiftScaleRotate , GridDistortion .”
MethodBubble boundary R-CNN: A multitask model for segmenting and reconstructing overlapping bubbles
Kang, Q., Ye, F., Li, Q., Li, R., Wang, J., Wang, H., Yu, H., Cheng, J., Li, X., & Yang, C. (2024) · Separation and Purification Technology · doi:10.1016/j.seppur.2024.130300 · Cited by 16
Malagoli, E., & Persio, L. D. (2025) · Mathematics · doi:10.3390/math13060893 · Cited by 20
A real–time detection framework for surface defects in ceramic tableware based on deep learning
Sun, P., Hua, C., Ding, W., & Hua, C. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128101 · Cited by 17
Vijayakumar, V., Ampatzidis, Y. G., Lacerda, C., Burks, T., Lee, W. S., & Schueller, J. K. (2025) · Biosystems Engineering · doi:10.1016/j.biosystemseng.2025.104288 · Cited by 16
Zhu, W., & Chen, K. (2026) · Scientific Reports · doi:10.1038/s41598-026-37938-5 · Cited by 28
Hua, A., Martin, K., Shen, Y., Chen, N., Mou, C., Sterk, M., Reinhard, B., Reinhard, F. F., Lee, S. J., Alibhai, S. K., et al. (2022) · PeerJ · doi:10.7717/peerj.13779 · Cited by 23
“To do this, we automatically transformed existing images using the Albumentations library (Buslaev et al., 2020) in the model training pipeline.”
MethodPatagonian Andes Landslides Inventory: The Deep Learning’s Way to Their Automatic Detection
Morales, B., Garcia-Pedrero, A. M., Lizama, E., Lillo‐Saavedra, M., Gonzalo‐Martín, C., Chen, N., & Somos‐Valenzuela, M. A. (2022) · Remote Sensing · doi:10.3390/rs14184622 · Cited by 18
Structural Augmentation in Seismic Data for Fault Prediction
Wang, S., Si, X., Cai, Z., & Cui, Y. (2022) · Applied Sciences · doi:10.3390/app12199796 · Cited by 19
Peat Drainage Ditch Mapping from Aerial Imagery Using a Convolutional Neural Network
Robb, C., Pickard, A., Williamson, J., Fitch, A., & Evans, C. (2023) · Remote Sensing · doi:10.3390/rs15020499 · Cited by 19
Rethinking Cooking State Recognition with Vision Transformers
Khan, A. M., Ashrafee, A., Sayera, R., Ivan, S., & Ahmed, S. (2022) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit57492.2022.10055869 · Cited by 17
“Random rotation, horizontal flip, conversion to Hue Saturation Value (HSV) form, random brightness-contrast, and random shift-scale were among the data augmentation techniques we applied to the training set to increase the size by five-fold using the augmentation tool ‘Albumentations’ [28].”
MethodIslam, M. Z., Naqvi, R. A., Haider, A., & Kim, H. S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106276 · Cited by 17
Zhu, J., He, G., & Zhou, P. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3284050 · Cited by 22
“augmentation based on Albumentations [31] to solve the shortage of datasets.”
BackgroundDrone Detection & Classification with Surveillance ‘Radar On-The-Move’ and YOLO
Haifawi, H., Fioranelli, F., Yarovoy, A. G., & van der Meer, R. (2023) · IEEE Radar Conference (RadarConf) · doi:10.1109/radarconf2351548.2023.10149588 · Cited by 16
“Thus, the data augmentation methods used in this approach are flip, translation, mosaic, hue, saturation, and value, denoted as ’albumentations’ [17].”
MethodTurley, J., Chenchiah, I. V., Martin, P. B., Liverpool, T. B., & Weavers, H. (2023) · eLife · doi:10.7554/elife.87949 · Cited by 21
Zvulunov, A., Lenevich, S., & Migacheva, N. B. (2023) · JMIR Dermatology · doi:10.2196/49278 · Cited by 16
“The images were augmented using the albumentations library [16,17] and shrunk to 384 × 384 pixels prior to feeding to the model [17].”
MethodGarcía‐Hidalgo, M., Garcia-Pedrero, A. M., Rozas, V., Sangüesa‐Barreda, G., García‐Cervigón, A. I., Resente, G., Wilmking, M., & Olano, J. M. (2024) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1327163 · Cited by 18
3D photogrammetry and deep‐learning deliver accurate estimates of epibenthic biomass
Marlow, J., Halpin, J. E., & Wilding, T. A. (2024) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.14313 · Cited by 21
Zheng, C., Jiang, Y., Lv, X., Nie, J., Liang, X., & Wei, Z. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3383066 · Cited by 16
Zhou, C., Wu, Y., Sterkens, W., Piessens, M., Vandewalle, P., & Peeters, J. R. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.04.024 · Cited by 17
A systematic comparison of deep learning methods for Gleason grading and scoring
Dominguez-Morales, J. P., Durán-López, L., Marini, N., Vicente-Díaz, S., Linares-Barranco, A., Atzori, M., & Müller, H. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103191 · Cited by 21
Brain tumor segmentation based on the U-NET++ network with efficientnet encoder
Chen, Y., Quan, L., Long, C., Chen, Y., Zu, L., & Huang, C. (2024) · Technology and Health Care · doi:10.3233/thc-248016 · Cited by 16
“Albumentations [9] is a powerful data augmentation tool that contains lots of data augmentation methods such as image resizing, scale, rotation, transpose, flipping, etc.”
BackgroundHøgstedt, E. B., Schellewald, C., Mester, R., & Stahl, A. (2024) · Aquaculture · doi:10.1016/j.aquaculture.2024.741535 · Cited by 16
Enhancing grain moisture prediction in multiple crop seasons using domain adaptation AI
Yang, M., Hsu, Y., Liu, T.-T., & Huang, H.-H. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110058 · Cited by 17
SAM-OCTA: Prompting segment-anything for OCTA image segmentation
Chen, X., Wang, C., Ning, H., Li, S., & Shen, M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107698 · Cited by 22
Kashin, A. S., Boiko, D. A., & Ananikov, V. P. (2021) · Small · doi:10.1002/smll.202007726 · Cited by 16
Marini, N., Atzori, M., Otálora, S., Marchand‐Maillet, S., & Müller, H. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00073 · Cited by 27
“Data augmentation is implemented with the Albumentations library [8].”
Image-Based Analysis of Dense Particle Mixtures via Mask R-CNN
Frei, M., & Kruis, F. E. (2022) · Eng—Advances in Engineering · doi:10.3390/eng3010007 · Cited by 18
CAIPI in Practice: Towards Explainable Interactive Medical Image Classification
Slany, E., Ott, Y., Scheele, S., Paulus, J., & Schmid, U. (2022) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-08341-9_31 · Cited by 22
Li, W., Zhan, W., Han, T., Wang, P., Liu, H., Xiong, M., & Hong, S. (2022) · Journal of Signal Processing Systems · doi:10.1007/s11265-022-01816-w · Cited by 16
“We use OpenCV, Numpy, Matplotlib, Python Image Library(PIL), and scikit-image modules to process images, use the Albumentations [47] library for online data augmentation, and use the Baidu Pad-dlePaddle 2.2.1 framework to build neural networks.”
MethodInfluentialLiu, H., Lv, H., Li, J., Liu, Y., & Deng, L. (2022) · Scientific Reports · doi:10.1038/s41598-022-23484-3 · Cited by 16
Efficient instance segmentation using deep learning for species identification in fish markets
García-D’Urso, N., Galán-Cuenca, A., Climent-Pérez, P., Saval-Calvo, M., Azorín-López, J., & Fuster-Guilló, A. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892945 · Cited by 20
“A series of different tools for the task were considered [26], [27], but finally CLoDSA [28] was used.”
MethodAiTLAS: Artificial Intelligence Toolbox for Earth Observation
Dimitrovski, I., Kitanovski, I., Panov, P., Kostovska, A., Simidjievski, N., & Kocev, D. (2023) · Remote Sensing · doi:10.3390/rs15092343 · Cited by 22
Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
Kalb, T., & Beyerer, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01869 · Cited by 24
Tang, H., Sun, N., Li, Y., & Xia, H. (2020) · medRxiv · doi:10.1101/2020.10.19.20215483 · Cited by 17
“All of these transformations were performed using Albumentations, a fast augmentation library[34].”
MethodZhang, Y., Xu, Y., Xu, T., Wang, C., Li, C., & Wang, H. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101433 · Cited by 16
Augmentation-Based Methodology for Enhancement of Trees Map Detalization on a Large Scale
Illarionova, S., Shadrin, D., Ignatiev, V., Shayakhmetov, S., Trekin, A., & Oseledets, I. V. (2022) · Remote Sensing · doi:10.3390/rs14092281 · Cited by 15
Chen, K.-H., Yang, C., Wang, H., Ma, H., & Lee, O. K. (2022) · JMIR AI · doi:10.2196/37508 · Cited by 15
“The MR images were then augmented with horizontal flipping and Gaussian noise [14].”
MethodUncovering Archaeological Sites in Airborne LiDAR Data With Data-Centric Artificial Intelligence
Canedo, D., Fonte, J., Gonçalves‐Seco, L., Vázquez, M., Dias, R., do Pereiro, T., Hipólito, J., Menéndez-Marsh, F., Georgieva, P., & Neves, A. J. R. (2023) · IEEE Access · doi:10.1109/access.2023.3290305 · Cited by 15
Probe conditioning via convolution neural network for scanning probe microscopy automation
Diao, Z., Hou, L., & Abe, M. (2023) · Applied Physics Express · doi:10.35848/1882-0786/acecd6 · Cited by 15
Local refinement mechanism for improved plant leaf segmentation in cluttered backgrounds
Ma, R., Fuentes, A., Yoon, S., Lee, W. Y., Kim, S. C., Kim, H., & Park, D. S. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1211075 · Cited by 15
“Frontiers in Plant Science 12 comparisons, all models were based on the Albumentation transformations method, with (w) and without (w/o) the inclusion of our refinement strategy (Buslaev et al., 2020).”
MethodImproving the mapping of coastal invasive species using UAV imagery and deep learning
Cruz, C. A., McGuinness, K., Perrin, P. M., O’Connell, J., Martin, J. R., & Connolly, J. (2023) · International Journal of Remote Sensing · doi:10.1080/01431161.2023.2251186 · Cited by 16
“The train image patches were subjected to augmentation techniques using the Albumentations library (Buslaev et al. 2020) in Python.”
Kozlov, K. S., Boiko, D. A., Detusheva, E. V., Detushev, K. V., Pentsak, E. O., Vereshchagin, A. N., & Ananikov, V. P. (2023) · Digital Discovery · doi:10.1039/d3dd00048f · Cited by 18
Open Problems in Computer Vision for Wilderness SAR and The Search for Patricia Wu-Murad
Manzini, T., & Murphy, R. R. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00409 · Cited by 15
Cheng, H., Chai, W., Hu, J., Ruan, W., Shi, M., Kim, H., Cao, Y., & Narazaki, Y. (2024) · Journal of Infrastructure Intelligence and Resilience · doi:10.1016/j.iintel.2024.100098 · Cited by 18
Multi-scale deep learning ensemble for segmentation of endometriotic lesions
Podda, A. S., Balia, R., Barra, S., Carta, S., Neri, M., Guerriero, S., & Piano, L. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09828-2 · Cited by 18
“Instead of the canonical augmentation methods offered by the Keras library, we opted for those provided by the Albumen-tation one [32], which implements a larger variety of transformations.”
Zeng, G., Wei, H.-N., Lu, K., Geng, G., & Weng, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3436130 · Cited by 17
Multi-class segmentation of temporomandibular joint using ensemble deep learning
Yoon, K., Kim, J., Kim, S., Huh, J., Kim, J., & Choi, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-69814-5 · Cited by 17
“Owing to the low contrast of MR images, the contrast-limited adaptive histogram equalization (CLAHE) technique 35 was implemented for the training subset utilizing the Albumentations Python library 36 .”
MethodRT-DETR-SoilCuc: detection method for cucumber germinationinsoil based environment
Li, Z., Wu, Y., Jiang, H., Lei, D., Pan, F., Qiao, J., Fu, X., & Guo, B. (2024) · Frontiers in Plant Science · doi:10.3389/fpls.2024.1425103 · Cited by 16
Metadata augmented deep neural networks for wild animal classification
Tøn, A., Ahmed, A., Imran, A. S., Ullah, M., & Azad, R. M. A. (2024) · Ecological Informatics · doi:10.1016/j.ecoinf.2024.102805 · Cited by 15
“The augmentation of the over-sampled images was performed with an augmentation pipeline using the Albumentations python package (Buslaev et al., 2018).”
MethodDominguez-Morales, J. P., Hernández‐Rodríguez, J., Durán-López, L., Conejo‐Mir, J., & Rodríguez, J. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3465929 · Cited by 16
From Schematics to Netlists – Electrical Circuit Analysis Using Deep-Learning Methods
Hemker, D., Maalouly, J., Mathis, H., Klos, R., & Ravanan, E. (2024) · Advances in radio science · doi:10.5194/ars-22-61-2024 · Cited by 16
A holistic framework to optimize embedding PV systems into building façades
Bakmohammadi, P., Narjabadifam, N., Jamshidi, M., & Gül, M. (2025) · Applied Energy · doi:10.1016/j.apenergy.2025.125288 · Cited by 15
Predicting uncertainty in vision-based satellite pose estimation using deep evidential regression
Dixon, T. O., Giles, S. A., & Gorodetsky, A. (2025) · Aerospace Science and Technology · doi:10.1016/j.ast.2025.110055 · Cited by 19
Strawberry harvest date prediction using multi-feature fusion deep learning in plant factory
Lin, Z., Liu, W., Wang, S., Pan, J., Fu, R., Chen, T., & Lin, T. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110174 · Cited by 17
Li, B., Zhou, J. Y., Gou, F., & Wu, J. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01847-3 · Cited by 18
Duan, R., Wang, Y., Chen, X., & Li, S. (2025) · Energy · doi:10.1016/j.energy.2025.136711 · Cited by 16
Solovyev, R. A., Melekhov, I., Lesonen, T., Vaattovaara, E., Tervonen, O. A., & Tiulpin, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-40605-9_11 · Cited by 16
“Our experiments were conducted in Keras [6] with Albumentations library [2] used for data augmentation.”
MethodDeep Depth From Aberration Map
Kashiwagi, M., Mishima, N., Kozakaya, T., & Hiura, S. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00417 · Cited by 16
“We select random crop [6], brightness [6] and random erasing [33] that do not affect blur.”
BackgroundAn Evaluation of DNN Architectures for Page Segmentation of Historical Newspapers
Liebl, B., & Burghardt, M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412571 · Cited by 23
“We used some data augmentation using the Albumentations library [21] with (1) rotation of up to ±10 degrees (applied always) and (2) contrast manipulation using default settings (applied with a probability of 90%).”
MethodPotholes Detection Using Deep Learning and Area Estimation Using Image Processing
Kharel, S., & Ragab, K. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82199-9_24 · Cited by 15
Review of Machine Learning Algorithms for Automatic Detection of Underground Objects in GPR Images
Amaral, L. C. M., Roshan, A., & Bayat, A. (2021) · Journal of Pipeline Systems Engineering and Practice · doi:10.1061/(asce)ps.1949-1204.0000632 · Cited by 18
Segmenting Skin Biopsy Images with Coarse and Sparse Annotations using U-Net
Nofallah, S., Mokhtari, M., Wu, W., Mehta, S., Knezevich, S. R., May, C. J., Chang, O. H., Lee, A. C., Elmore, J. G., & Shapiro, L. G. (2022) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-022-00641-8 · Cited by 15
“We used the fast augmentation library for these augmentation techniques [23].”
MethodSemantic segmentation of explosive volcanic plumes through deep learning
Wilkes, T. C., Pering, T. D., & McGonigle, A. J. S. (2022) · Computers & Geosciences · doi:10.1016/j.cageo.2022.105216 · Cited by 18
Döllinger, M., Schraut, T., Henrich, L., Chhetri, D. K., Echternach, M., Johnson, A. M., Kunduk, M., Maryn, Y., Patel, R. R., Samlan, R. A., et al. (2022) · Applied Sciences · doi:10.3390/app12199791 · Cited by 17
Thalassemia Diagnosis Through Medical Imaging: A New Artificial Intelligence-Based Framework
Zaylaa, A. J., Makki, M., & Kassem, R. (2022) · International Conference on Smart Systems and Power Management (IC2SPM) · doi:10.1109/ic2spm56638.2022.9988891 · Cited by 15
“Different techniques were applied, such as affine transformations, noise, and filters with tweaked and tuned parameters in a way that retains the learnable features of the images and maintain high information instead of data loss and data leakage [14].”
MethodZero-shot ear cross-dataset transfer for person recognition on mobile devices
Freire-Obregón, D., Marsico, M. D., Barra, P., Lorenzo-Navarro, J., & Castrillón-Santana, M. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.01.012 · Cited by 19
End-to-end Multiple Instance Learning with Gradient Accumulation
Andersson, A., Koriakina, N., Sladoje, N., & Lindblad, J. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020801 · Cited by 20
“During the creation of Imagenette-bags we resize the images to the size of 112×112 pixels using bilinear interpolation and perform a set of random augmentations (see [12] for details) using Albumentations package [18].”
MethodIterLUNet: Deep Learning Architecture for Pixel-Wise Crack Detection in Levee Systems
Panta, M., Hoque, M. T., Abdelguerfi, M., & Flanagin, M. C. (2023) · IEEE Access · doi:10.1109/access.2023.3241877 · Cited by 15
“techniques [32], and analyzing the performance of the baseline method.”
Method
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.