{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/augmentor-an-image-augmentation-library-for","title":"Augmentor: An Image Augmentation Library for Machine Learning","arxiv_id":"1708.04680","date":"2017-08-11","proceeding":null,"authors":["Marcus D. Bloice","Christof Stocker","Andreas Holzinger"],"abstract":"The generation of artificial data based on existing observations, known as\ndata augmentation, is a technique used in machine learning to improve model\naccuracy, generalisation, and to control overfitting. Augmentor is a software\npackage, available in both Python and Julia versions, that provides a high\nlevel API for the expansion of image data using a stochastic, pipeline-based\napproach which effectively allows for images to be sampled from a distribution\nof augmented images at runtime. Augmentor provides methods for most standard\naugmentation practices as well as several advanced features such as\nlabel-preserving, randomised elastic distortions, and provides many helper\nfunctions for typical augmentation tasks used in machine learning.","url_abs":"http://arxiv.org/abs/1708.04680v1","url_pdf":"http://arxiv.org/pdf/1708.04680v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/Evizero/Augmentor.jl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/ChenXiao61/Img_augmentor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/Rahul-Venugopal/Image-augmentation_1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/UnofficialJuliaMirror/Augmentor.jl-0612f1b9-51e2-5127-9fc2-313c368ba66d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/UnofficialJuliaMirrorSnapshots/Augmentor.jl-0612f1b9-51e2-5127-9fc2-313c368ba66d","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"augmentor-an-image-augmentation-library-for","repo_url":"https://github.com/simonlousky/alteredAugmentor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-augmentation","task_name":"Image Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}