{"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/why-does-my-medical-ai-look-at-pictures-of","title":"Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries","arxiv_id":"2306.17555","date":"2023-06-30","proceeding":null,"authors":["Frederic Jonske","Moon Kim","Enrico Nasca","Janis Evers","Johannes Haubold","René Hosch","Felix Nensa","Michael Kamp","Constantin Seibold","Jan Egger","Jens Kleesiek"],"abstract":"It is an open secret that ImageNet is treated as the panacea of pretraining. Particularly in medical machine learning, models not trained from scratch are often finetuned based on ImageNet-pretrained models. We posit that pretraining on data from the domain of the downstream task should almost always be preferred instead. We leverage RadNet-12M, a dataset containing more than 12 million computed tomography (CT) image slices, to explore the efficacy of self-supervised pretraining on medical and natural images. Our experiments cover intra- and cross-domain transfer scenarios, varying data scales, finetuning vs. linear evaluation, and feature space analysis. We observe that intra-domain transfer compares favorably to cross-domain transfer, achieving comparable or improved performance (0.44% - 2.07% performance increase using RadNet pretraining, depending on the experiment) and demonstrate the existence of a domain boundary-related generalization gap and domain-specific learned features.","url_abs":"https://arxiv.org/abs/2306.17555v1","url_pdf":"https://arxiv.org/pdf/2306.17555v1.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":"why-does-my-medical-ai-look-at-pictures-of","repo_url":"https://github.com/tio-ikim/transfer-learning-across-domain-boundaries","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computed-tomography-ct","task_name":"Computed Tomography (CT)"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}