{"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/cats-or-cat-scans-transfer-learning-from","title":"Cats or CAT scans: transfer learning from natural or medical image source datasets?","arxiv_id":"1810.05444","date":"2018-10-12","proceeding":null,"authors":["Veronika Cheplygina"],"abstract":"Transfer learning is a widely used strategy in medical image analysis.\nInstead of only training a network with a limited amount of data from the\ntarget task of interest, we can first train the network with other, potentially\nlarger source datasets, creating a more robust model. The source datasets do\nnot have to be related to the target task. For a classification task in lung CT\nimages, we could use both head CT images, or images of cats, as the source.\nWhile head CT images appear more similar to lung CT images, the number and\ndiversity of cat images might lead to a better model overall. In this survey we\nreview a number of papers that have performed similar comparisons. Although the\nanswer to which strategy is best seems to be \"it depends\", we discuss a number\nof research directions we need to take as a community, to gain more\nunderstanding of this topic.","url_abs":"http://arxiv.org/abs/1810.05444v2","url_pdf":"http://arxiv.org/pdf/1810.05444v2.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":"cats-or-cat-scans-transfer-learning-from","repo_url":"https://github.com/shizuo-kaji/PretrainCNNwithNoData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"cats-or-cat-scans-transfer-learning-from","repo_url":"https://github.com/vcheplygina/cats-scans","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}