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 101–200 of 1,006
Training Strategies and Data Augmentations in CNN-based DeepFake Video Detection
Bondi, L., Daniele Cannas, E., Bestagini, P., & Tubaro, S. (2020) · 2020 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs49906.2020.9360901 · Cited by 86
“All the proposed experiments are performed with the Albumentations [37] framework.”
MethodSherwood, A. A., Sherwood, I., Setzer, F. C., Sheela Devi, K., Shamili, J. V., John, C. S., & Schwendicke, F. (2021) · Journal of Endodontics · doi:10.1016/j.joen.2021.09.009 · Cited by 110
Eff-UNet++: A novel architecture for plant leaf segmentation and counting
Bhagat, S., Kokare, M., Haswani, V., Hambarde, P., & Kamble, R. M. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101583 · Cited by 107
Underwater Image Enhancement With Reinforcement Learning
Sun, S., Wang, H., Zhang, H., Li, M., Xiang, M., Luo, C. L., & Ren, P. (2022) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2022.3152519 · Cited by 99
Ge, Y., Lin, S., Zhang, Y., Li, Z., Cheng, H., Dong, J., Shao, S., Zhang, J., Qi, X., & Wu, Z. (2022) · Machines · doi:10.3390/machines10060489 · Cited by 99
Overcoming data scarcity in biomedical imaging with a foundational multi-task model
Schäfer, R., Nicke, T., Höfener, H., Lange, A., Merhof, D., Feuerhake, F., Schulz, V., Lotz, J., & Kiessling, F. M. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00662-z · Cited by 134
“For 2D images, we used standard augmentations using the Albu-mentations library 62 (CLAHE, Sharpen, Emboss, RandomBrightness-Contrast, RandomGamma, Gaussnoise and HueSaturationValue, ShiftScaleRotate).”
BAGLS, a multihospital Benchmark for Automatic Glottis Segmentation
Gómez, P., Kist, A. M., Schlegel, P., Berry, D. A., Chhetri, D. K., Dürr, S., Echternach, M., Johnson, A. M., Kniesburges, S., Kunduk, M., et al. (2020) · Scientific Data · doi:10.1038/s41597-020-0526-3 · Cited by 95
Marzola, F., van Alfen, N., Doorduin, J., & Meiburger, K. M. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104623 · Cited by 91
Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks
Shvets, A. A., Iglovikov, V., Rakhlin, A., & Kalinin, A. A. (2018) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2018.00098 · Cited by 90
Self-citationDeveloping and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps
Nitze, I., Heidler, K., Barth, S., & Grosse, G. (2021) · Remote Sensing · doi:10.3390/rs13214294 · Cited by 88
On the Cross-dataset Generalization in License Plate Recognition
Laroca, R., Cardoso, E., Lucio, D. R., Estevam, V., & Menotti, D. (2022) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010846800003124 · Cited by 101
Asphalt pavement fatigue crack severity classification by infrared thermography and deep learning
Liu, F., Liu, J., & Wang, L. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104575 · Cited by 90
Casado-García, Á., Domínguez, C., García-Domínguez, M., Heras, J., Inés, A., Mata, E. J., & Pascual, V. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-2931-1 · Cited by 86
“Imgaug [11] provides more than 40 augmentation techniques, and albumentations [47] is the fastest augmentation library.”
BackgroundBabakhin, Y., Sanakoyeu, A., & Kitamura, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33676-9_15 · Cited by 92
Deep Image Denoising With Adaptive Priors
Jiang, B., Lu, Y., Wang, J., Lu, G., & Zhang, D. D. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3149518 · Cited by 89
“Tomato-Village”: a dataset for end-to-end tomato disease detection in a real-world environment
Gehlot, M., Saxena, R. K., & Gandhi, G. C. (2023) · Multimedia Systems · doi:10.1007/s00530-023-01158-y · Cited by 80
“To improve further, seven off-line augmentations RGBShift, RandomBrightnessContrast, Rotate up to 90 degrees, RandomRotate90, HorizontalFlip, VerticalFlip, and Randomcrop with 30% pixel reductions were used with the help of Albumentations [37] library.”
MethodThe face deepfake detection challenge
Guarnera, L., Giudice, O., Guarnera, F., Ortis, A., Puglisi, G., Paratore, A., Bui, L. M. Q., Fontani, M., Coccomini, D. A., Caldelli, R., et al. (2022) · Journal of Imaging · doi:10.3390/jimaging8100263 · Cited by 79
“As a first step, indeed, participants created an augmented version of the training dataset by applying the following augmentation methods using the Albumentations library [48]:”
MethodTaşar, O., Giros, A., Tarabalka, Y., Alliez, P., & Clerc, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3006161 · Cited by 91
“of CNNs, another common approach is to perform online data augmentation with random color change [6].”
MethodPhotovoltaics Plant Fault Detection Using Deep Learning Techniques
Jumaboev, S., Jurakuziev, D., & Lee, M. (2022) · Remote Sensing · doi:10.3390/rs14153728 · Cited by 91
Deep Learning for Regular Change Detection in Ukrainian Forest Ecosystem With Sentinel-2
Isaienkov, K., Yushchuk, M., Khramtsov, V., & Seliverstov, O. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3034186 · Cited by 91
“…furtherrescalingtotheinitialsize),randombrightness,and contrastchanging; 2) elastic and grid transformations (for more details, see [9] and [54]); and 3) mask dropout (zeroing out mask/image regions corresponding to instance at mask), which were applied with some predefined…”
MethodPrior Attention Network for Multi-Lesion Segmentation in Medical Images
Zhao, X., Zhang, P., Song, F., Ma, C., Fan, G., Sun, Y., Feng, Y., & Zhang, G. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3197180 · Cited by 88
“Data augmentation is performed with Albumentations[35] in our training process to reduce overfitting and improve generalization capacity.”
MethodU-Net Ensemble for Enhanced Semantic Segmentation in Remote Sensing Imagery
Dimitrovski, I., Spasev, V., Loshkovska, S., & Kitanovski, I. (2024) · Remote Sensing · doi:10.3390/rs16122077 · Cited by 98
ImageNet Pre-trained CNNs for JPEG Steganalysis
Yousfi, Y., Butora, J., Khvedchenya, E., & Fridrich, J. (2020) · IEEE International Workshop on Information Forensics and Security · doi:10.1109/wifs49906.2020.9360897 · Cited by 90
“All training augmentations were performed using the Albumentations library [31].”
MethodSelf-citationSafari, M., Fatemi, A. B., & Archambault, L. (2023) · BMC Medical Imaging · doi:10.1186/s12880-023-01160-w · Cited by 77
“The following data augmentation methods [42] were used; (2) • Horizontal and vertical flips, random rotation of up to 20 ◦ , and random grid distortion all with probability of 30% .”
MethodWang, Y., Sun, Q., Liu, Z., & Gu, L. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103945 · Cited by 83
Improved CT-based Osteoporosis Assessment with a Fully Automated Deep Learning Tool
Pickhardt, P. J., Nguyễn, T. V., Perez, A. A., Graffy, P. M., Jang, S., Summers, R. M., & Garrett, J. W. (2022) · Radiology Artificial Intelligence · doi:10.1148/ryai.220042 · Cited by 86
Deepfake Detection Scheme Based on Vision Transformer and Distillation
Heo, Y. J., Choi, Y. J., Lee, Y., & Kim, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01353 · Cited by 38
“We augmented our training data using Albumentations [7].”
MethodRoad Segmentation using U-Net architecture
Abderrahim, N. Y. Q., Saadane, A., & Azmi, R. (2020) · IEEE International Conference of Moroccan Geomatics (MORGEO) · doi:10.1109/morgeo49228.2020.9121887 · Cited by 79
“To generate more images we used albumentations library [18], it has been reported as a fast and flexible implementation for augmentation data, in our case we used basic tranformation such as flip and elasric transform as shown in the Fig.”
MethodLandslide susceptibility prediction based on image semantic segmentation
Du, B., Zhao, Z., Hu, X., Wu, G., Han, L., Sun, L., & Gao, Q. (2021) · Computers & Geosciences · doi:10.1016/j.cageo.2021.104860 · Cited by 80
Classification and Understanding of Cloud Structures via Satellite Images with EfficientUNet
Ahmed, T., & Sabab, N. H. N. (2021) · SN Computer Science · doi:10.1007/s42979-021-00981-2 · Cited by 79
Detecting Gan-Generated Images by Orthogonal Training of Multiple CNNs
Mandelli, S., Bonettini, N., Bestagini, P., & Tubaro, S. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897310 · Cited by 115
“The parameters are those defined in [16].”
Early detection of visual impairment in young children using a smartphone-based deep learning system
Chen, W., Li, R., Yu, Q., Xu, A., Feng, Y., Wang, R., Zhao, L., Lin, Z., Yang, Y., Lin, D., et al. (2023) · Nature Medicine · doi:10.1038/s41591-022-02180-9 · Cited by 82
“All data augmentation processes were based on a publicly available Python library known as Albumentations 53 .”
MethodDeep Learning-Based Weed Detection Using UAV Images: A Comparative Study
Shahi, T. B., Dahal, S., Sitaula, C., Neupane, A., & Guo, W. W. (2023) · Drones · doi:10.3390/drones7100624 · Cited by 75
“The second transformation includes the combination of vertical flip with random rotation and grid [47].”
BackgroundDisease detection in rice leaves using transfer learning techniques
Kathiresan, G. S., Anirudh, M., Nagharjun, M., & Karthik, R. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1911/1/012004 · Cited by 72
“Initially all images underwent transforms using the Albumentations augmentation library to address the issues of color similarity discussed in section 2 [26].”
MethodA hybrid deep convolutional neural network for accurate land cover classification
Wambugu, N. M., Chen, Y., Xiao, Z., Wei, M., Bello, S. A., Marcato, J., & Li, J. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102515 · Cited by 90
“To achieve this, we employed the albu-mentations library (Buslaev et al., 2020), which provides several flexible and efficient image augmentation functions relating to color, contrast, brightness, and other geometric transformations.”
MethodBerne, J. V., Saadi, S. B., Politis, C., & Jacobs, R. (2023) · Journal of Dentistry · doi:10.1016/j.jdent.2023.104581 · Cited by 81
Generative Adversarial Networks (GANs) for Image Augmentation in Farming: A Review
Rahman, Z. U., Asaari, M. S. M., Ibrahim, H., Abidin, I. S. Z., & Ishak, M. K. (2024) · IEEE Access · doi:10.1109/access.2024.3505989 · Cited by 91
DropMessage: Unifying Random Dropping for Graph Neural Networks
Fang, T., Xiao, Z., Wang, C., Xu, J., Yang, X., & Yang, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25545 · Cited by 78
“These random dropping methods can also be regarded as special forms of data augmentation (Shorten and Khoshgoftaar 2019; Frid-Adar et al. 2018; Buslaev et al. 2020; Ding et al. 2022; Velickovic et al. 2019), with the advantage of not requiring parameter estimation (Papp et al.”
BackgroundBrain tumour detection using machine and deep learning: a systematic review
Rasool, N., & Bhat, J. I. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19333-2 · Cited by 99
Taşar, O., Tarabalka, Y., Giros, A., Alliez, P., & Clerc, S. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00104 · Cited by 83
“Oftentimes, it is a good practice to perform data augmentation [4] to enlarge the training data and to reduce the risk of over-fitting.”
MethodYOLOPX: Anchor-free multi-task learning network for panoptic driving perception
Zhan, J., Luo, Y., Guo, C., Wu, Y., Meng, J., & Liu, J. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110152 · Cited by 90
Maize tassel detection with CA-YOLO for UAV images in complex field environments
Jia, Y., Fu, K., Lan, H., Wang, X., & Su, Z. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108562 · Cited by 74
Runz, M., Rusche, D., Schmidt, S., Weihrauch, M. R., Hesser, J., & Weis, C. (2021) · Diagnostic Pathology · doi:10.1186/s13000-021-01126-y · Cited by 68
“It should be noted that a standard color normalization to the mean and standard deviation as well as data augmentation with the albu-mentations package [27] is carried out in the standard training setting.”
MethodTraining on Polar Image Transformations Improves Biomedical Image Segmentation
Benčević, M., Galić, I., Habijan, M., & Babin, D. (2021) · IEEE Access · doi:10.1109/access.2021.3116265 · Cited by 70
“• A 30% chance for a grid distortion, details of which are described in [24].”
BackgroundVision Transformer based COVID-19 Detection using Chest X-rays
Krishnan, K. S., & Krishnan, K. S. (2021) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc53510.2021.9609375 · Cited by 76
“The COVID-19 images are up-sampled using image augmentation techniques with the help of albumentations [13] library.”
MethodBack, S., Lee, S., Shin, S., Yu, Y., Yuk, T., Jong, S., Ryu, S., & Lee, K. (2021) · IEEE Access · doi:10.1109/access.2021.3054403 · Cited by 76
“For data augmentation, a similar pipeline proposed by [31] was utilized using the Albumentation library [56].”
MethodMarini, N., Otálora, S., Müller, H., & Atzori, M. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102165 · Cited by 79
Boston, T., van Dijk, A. I. J. M., Larraondo, P., & Thackway, R. (2022) · Remote Sensing · doi:10.3390/rs14143396 · Cited by 80
Chen, R., Cai, Z., & Cao, W. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3134762 · Cited by 77
“We adopt the Albumentations [46] method to realize geometric transformation (horizontal and vertical random flips and random hole cutting), chromatic transformation (contrast, saturation, and luminance), and simulated noise (random fog and motion blur).”
MethodHigh-resolution photoacoustic microscopy with deep penetration through learning
Cheng, S., Zhou, Y., Chen, J., Li, H., Wang, L., & Lai, P. (2021) · Photoacoustics · doi:10.1016/j.pacs.2021.100314 · Cited by 68
“After that, considering the training of deep neural network requires a large data set but the collected data was limited from experiment, data augmentation [41 – 43] was conducted using a Python library Albumentations [44].”
MethodDBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection
Wang, J., Yang, J., Yu, L., Dong, H., Yun, K., & Wang, Y. (2021) · Information · doi:10.3390/info12110474 · Cited by 65
“In total, 15 subcategories are noted, and the image around 255 × 470 × 3 pixels.”
BackgroundWang, Z., Chen, M., Guo, Y., Li, Z., & Yu, Q. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3250385 · Cited by 64
“During training, we apply different data augmentation strategies on source and target samples using Albumentations [57] with the default parameter setting.”
MethodLiver, kidney and spleen segmentation from CT scans and MRI with deep learning: A survey
Altini, N., Prencipe, B., Cascarano, G. D., Brunetti, A., Brunetti, G., Triggiani, V., Carnimeo, L., Marino, F., Guerriero, A., Villani, L., et al. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.08.157 · Cited by 74
Deep learning with visual explanations for leakage defect segmentation of metro shield tunnel
Feng, S. J., Feng, Y., Zhang, X., & Chen, Y. H. (2023) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2023.105107 · Cited by 65
DermoSegDiff: A Boundary-Aware Segmentation Diffusion Model for Skin Lesion Delineation
Bozorgpour, A., Sadegheih, Y., Kazerouni, A., Azad, R., & Merhof, D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-46005-0_13 · Cited by 86
Choi, H.-R., Siadari, T. S., Kim, J., Huh, K., Yi, W.-J., Lee, S.-S., & Heo, M.-S. (2022) · Forensic Sciences Research · doi:10.1080/20961790.2022.2034714 · Cited by 63
“The data augmentation was performed using the Albumentations library during the training to increase the amount of data for deep learning by modifying the images including the flipping, manipulation, and contrast normalisation of the images [18].”
MethodEnhanced deepfake detection with densenet and cross-vit
Siddiqui, F., Yang, J., Xiao, S., & Fahad, M. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126150 · Cited by 62
Monitoring sugar crystallization with deep neural networks
Zhang, J., Meng, Y., Wu, J., Qin, J., Wang, H., Yao, T., & Yu, S. (2020) · Journal of Food Engineering · doi:10.1016/j.jfoodeng.2020.109965 · Cited by 66
Approach to weld segmentation and defect classification in radiographic images of pipe welds
Golodov, V. A., & Maltseva, A. A. (2021) · NDT & E International · doi:10.1016/j.ndteint.2021.102597 · Cited by 67
Automatic Fungi Recognition: Deep Learning Meets Mycology
Picek, L., Šulc, M., Matas, J., Heilmann‐Clausen, J., Jeppesen, T. S., & Lind, E. (2022) · Sensors · doi:10.3390/s22020633 · Cited by 77
Cheng, L., Tong, Z., Xie, S., & Kersemans, M. (2022) · Composite Structures · doi:10.1016/j.compstruct.2022.115543 · Cited by 63
“"Albumentations: fast and flexible image augmentations."”
MethodObject-level benchmark for deep learning-based detection and classification of weed species
Hasan, A. S. M. M., Diepeveen, D., Laga, H., Jones, M. G. K., & Sohel, F. A. (2023) · Crop Protection · doi:10.1016/j.cropro.2023.106561 · Cited by 71
Plant recognition by AI: Deep neural nets, transformers, and kNN in deep embeddings
Picek, L., Sulc, M., Patel, Y. J., & Matas, J. E. S. (2022) · Frontiers in Plant Science · doi:10.3389/fpls.2022.787527 · Cited by 51
“While training, we employ a few data augmentation techniques from the Albumentations library (Buslaev et al., 2020).”
MethodAn Efficient Hybrid CNN Classification Model for Tomato Crop Disease
Sanida, M. V., Sanida, T., Sideris, A., & Dasygenis, M. (2023) · Technologies · doi:10.3390/technologies11010010 · Cited by 71
A Novel Approach to Data Augmentation for Pavement Distress Segmentation
Mazzini, D., Napoletano, P., Piccoli, F., & Schettini, R. (2020) · Computers in Industry · doi:10.1016/j.compind.2020.103225 · Cited by 66
Deployed Deep Learning Kidney Segmentation for Polycystic Kidney Disease MRI
Goel, A., Shih, G., Riyahi, S., Jeph, S., Dev, H., Hu, R., Romano, D., Teichman, K., Blumenfeld, J. D., Barash, I., et al. (2022) · Radiology Artificial Intelligence · doi:10.1148/ryai.210205 · Cited by 60
“Training data were augmented using affine transformations (17).”
MethodZou, Z., Chen, C., Liu, Z., Zhang, Z., Liang, J., Chen, H., & Wang, L. (2022) · Remote Sensing · doi:10.3390/rs14164001 · Cited by 60
Serouart, M., Madec, S., David, É., Velumani, K., López‐Lozano, R., Weiss, M., & Baret, F. (2022) · Plant Phenomics · doi:10.34133/2022/9803570 · Cited by 69
“Patches of 512 x 512 pixels were used for training after data 107 augmentation based on the Albumentations library [30].”
MethodAddressing materials’ microstructure diversity using transfer learning
Goetz, A., Durmaz, A. R., Müller, M. J., Thomas, A., Britz, D., Kerfriden, P., & Eberl, C. (2022) · npj Computational Materials · doi:10.1038/s41524-022-00703-z · Cited by 65
The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images
Mohanty, S. P., Singhal, G., Scuccimarra, E. A., Kebaili, D., Héritier, H., Boulanger, V., & Salathé, M. (2022) · Frontiers in Nutrition · doi:10.3389/fnut.2022.875143 · Cited by 72
“To avoid over-fitting, we used fairly aggressive data augmentation, powered by the albumentations library (27).”
MethodLi-SegPNet: Encoder-Decoder Mode Lightweight Segmentation Network for Colorectal Polyps Analysis
Sharma, P., Gautam, A., Maji, P., Pachori, R. B., & Balabantaray, B. K. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3216269 · Cited by 62
“Therefore, to compensate for the data limitation, we use data augmentation using Albumentations [37] library.”
MethodDeep Learning Methods for Screening Pulmonary Tuberculosis Using Chest X-rays
Dasanayaka, C., & Dissanayake, M. B. (2020) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2020.1808532 · Cited by 69
Resources for image-based high-throughput phenotyping in crops and data sharing challenges
Danilevicz, M. F., Bayer, P. E., Nestor, B. J., Bennamoun, M., & Edwards, D. (2021) · PLANT PHYSIOLOGY · doi:10.1093/plphys/kiab301 · Cited by 70
Emeksiz, C., & Tan, M. (2022) · Energy · doi:10.1016/j.energy.2022.123785 · Cited by 58
Image-Based High-Throughput Detection and Phenotype Evaluation Method for Multiple Lettuce Varieties
Du, J., Lu, X., Fan, J., Qin, Y., Yang, X., & Guo, X. (2020) · Frontiers in Plant Science · doi:10.3389/fpls.2020.563386 · Cited by 59
Klein, S., Quaas, A., Quantius, J., Löser, H., Meinel, J., Peifer, M., Wagner, S., Gattenlöhner, S., Wittekindt, C., Doeberitz, M. V. K., et al. (2020) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-20-3596 · Cited by 60
“steps were applied, including stain normalization onH&E images (27), as well as gray-scale augmentation with a ten-percent probability using Albumentations (28).”
MethodCheng, L., & Kersemans, M. (2022) · Composites Part B Engineering · doi:10.1016/j.compositesb.2022.110309 · Cited by 60
“The key parameters for each technique are listed in Fig.9, where p denotes probability, and additional information on the parameters is available in the official documents of Albumentations [39].”
MethodMSMatch: Semisupervised Multispectral Scene Classification With Few Labels
Gomez, P., & Meoni, G. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3126082 · Cited by 55
EmbryoNet: using deep learning to link embryonic phenotypes to signaling pathways
Čapek, D., Safroshkin, M., Morales-Navarrete, H. A., Toulany, N., Arutyunov, G., Kurzbach, A., Bihler, J. I., Hagauer, J., Kick, S., Jones, F. C., et al. (2023) · Nature Methods · doi:10.1038/s41592-023-01873-4 · Cited by 62
Diabetic foot ulcers segmentation challenge report: Benchmark and analysis
Yap, M. H., Cassidy, B., Byra, M., Liao, T.-Y., Yi, H., Galdrán, A., Chen, Y.-H., Brüngel, R., Koitka, S., Friedrich, C. M., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103153 · Cited by 67
Karpyshev, P., Ilin, V., Kalinov, I., Petrovsky, A., & Tsetserukou, D. (2021) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/ieeeconf49454.2021.9382649 · Cited by 54
Densely-Populated Traffic Detection Using YOLOv5 and Non-maximum Suppression Ensembling
Rahman, R., Azad, Z. B., & Hasan, M. B. (2021) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-6636-0_43 · Cited by 62
“To resolve this issue, we used augmentation using tools from Roboflow 1 and Albumentations library [19] for image augmentation.”
MethodGaNDLF: the generally nuanced deep learning framework for scalable end-to-end clinical workflows
Pati, S., Thakur, S. P., Hamamcı, İ. E., Baid, U., Baheti, B., Bhalerao, M., Güley, O., Mouchtaris, S., Lang, D., Thermos, S., et al. (2023) · Communications Engineering · doi:10.1038/s44172-023-00066-3 · Cited by 38
Toward Robust and Unconstrained Full Range of Rotation Head Pose Estimation
Hempel, T., Abdelrahman, A. A., & Al-Hamadi, A. K. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378180 · Cited by 82
“To exploit full generalization potential, we also extensively augment our training data using Albumentations [61] by applying random horizontal flipping, random scaling and cropping, random rotation up to [ − 45, + 45] degrees, random occlusions, and further image color operations including random…”
MethodDigital tongue image analyses for health assessment
Xie, J., Jing, C., Zhang, Z., Xu, J., Duan, Y., & Xu, D. H. (2021) · Medical Review · doi:10.1515/mr-2021-0018 · Cited by 63
“In the experiment, we performed data augmentation usingAlbumentations, a python library for fast and flexible image augmentations [150].”
MethodProbabilistic SAR-based water segmentation with adapted Bayesian convolutional neural network
Hertel, V., Chow, C., Wani, O., Wieland, M., & Martinis, S. (2022) · Remote Sensing of Environment · doi:10.1016/j.rse.2022.113388 · Cited by 62
Actin polymerisation and crosslinking drive left-right asymmetry in single cell and cell collectives
Tee, Y. H., Goh, W. J., Yong, X., Ong, H. T., Hu, J., Tay, I. Y. Y., Shi, S., Jalal, S., Barnett, S. F. H., Kanchanawong, P., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-35918-1 · Cited by 59
EasyAug: An Automatic Textual Data Augmentation Platform for Classification Tasks
Qiu, S., Xu, B., Zhang, J., Wang, Y., Shen, X., de Melo, G., Long, C., & Li, X. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366424.3383552 · Cited by 54
“In light of this, image data augmenting libraries such as Albumentations [1], Augmentor [2], and Imgaug [6], which integrate various augmentation techniques have been very useful for practitioners.”
BackgroundSelf-supervised audiovisual representation learning for remote sensing data
Heidler, K., Mou, L., Hu, D., Jin, P., Li, G., Gan, C., Wen, J.-R., & Zhu, X. X. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.103130 · Cited by 70
“Efficient data augmentations were enabled by the albumentations python library [48].”
Image2SMILES: Transformer‐Based Molecular Optical Recognition Engine**
Khokhlov, I., Krasnov, L. V., Fedorov, M. V., & Sosnin, S. (2022) · Chemistry - Methods · doi:10.1002/cmtd.202100069 · Cited by 56
Shunying, W., Ya'nan, Z., Xianzeng, Y., Feng, L., Wu, T., & Jiancheng, L. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107683 · Cited by 52
Improving Medical Vision-Language Contrastive Pretraining With Semantics-Aware Triage
Liu, B., Lu, D., Wei, D., Wu, X., Wang, Y., Zhang, Y., & Zheng, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3294980 · Cited by 72
“The Albumentations [5] Python library is used for augmentations with a probability of 0.5, including rotation (within ± 10 ) and resizing (within [0.9, 1.1]), following GLoRIA.”
MethodInfluentialLi, Y., Sun, Z. Y., Li, Y., Yang, H., Liu, X., & He, W. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111287 · Cited by 53
Ullah, N., Guzmán‐Aroca, F., Alvarez, F. M., Falco, I. D., & Sannino, G. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103665 · Cited by 61
Image Compositing for Segmentation of Surgical Tools Without Manual Annotations
García-Peraza-Herrera, L. C., Fidon, L., D’Ettorre, C., Stoyanov, D. V., Vercauteren, T. K., & Ourselin, S. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3057884 · Cited by 64
“Blended images are augmented with a set of techniques from Albumen-tations [38].”
An ensemble-based approach for automated medical diagnosis of malaria using EfficientNet
Marques, G., Ferreras, A., & Díez, I. D. L. T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12624-6 · Cited by 58
Cheng, Z., Huo, G., & Li, H. (2022) · Remote Sensing · doi:10.3390/rs14020355 · Cited by 56
Delplanque, A., Foucher, S., Théau, J., Bussière, E. M. S., Vermeulen, C., & Lejeune, P. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.01.025 · Cited by 67
Robotic Cable Routing with Spatial Representation
Jin, S., Lian, W., Wang, C., Tomizuka, M., & Schaal, S. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3158377 · Cited by 68
Song, J. H., Hong, Y., Kim, E. R., Kim, S., & Sohn, I. (2022) · Journal of Gastroenterology · doi:10.1007/s00535-022-01894-4 · Cited by 53
“For each patch-image, common image augmentation methods, including flipping, rotation, and color change, were used to obtain a more robust model throughout the training process [51].”
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.