{"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/cfcm-segmentation-via-coarse-to-fine-context","title":"CFCM: Segmentation via Coarse to Fine Context Memory","arxiv_id":"1806.01413","date":"2018-06-04","proceeding":null,"authors":["Fausto Milletari","Nicola Rieke","Maximilian Baust","Marco Esposito","Nassir Navab"],"abstract":"Recent neural-network-based architectures for image segmentation make\nextensive usage of feature forwarding mechanisms to integrate information from\nmultiple scales. Although yielding good results, even deeper architectures and\nalternative methods for feature fusion at different resolutions have been\nscarcely investigated for medical applications. In this work we propose to\nimplement segmentation via an encoder-decoder architecture which differs from\nany other previously published method since (i) it employs a very deep\narchitecture based on residual learning and (ii) combines features via a\nconvolutional Long Short Term Memory (LSTM), instead of concatenation or\nsummation. The intuition is that the memory mechanism implemented by LSTMs can\nbetter integrate features from different scales through a coarse-to-fine\nstrategy; hence the name Coarse-to-Fine Context Memory (CFCM). We demonstrate\nthe remarkable advantages of this approach on two datasets: the Montgomery\ncounty lung segmentation dataset, and the EndoVis 2015 challenge dataset for\nsurgical instrument segmentation.","url_abs":"http://arxiv.org/abs/1806.01413v1","url_pdf":"http://arxiv.org/pdf/1806.01413v1.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":"cfcm-segmentation-via-coarse-to-fine-context","repo_url":"https://github.com/faustomilletari/CFCM-2D","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"cfcm-segmentation-via-coarse-to-fine-context","repo_url":"https://github.com/alvchn/fcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"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}