{"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/the-importance-of-skip-connections-in","title":"The Importance of Skip Connections in Biomedical Image Segmentation","arxiv_id":"1608.04117","date":"2016-08-14","proceeding":null,"authors":["Michal Drozdzal","Eugene Vorontsov","Gabriel Chartrand","Samuel Kadoury","Chris Pal"],"abstract":"In this paper, we study the influence of both long and short skip connections\non Fully Convolutional Networks (FCN) for biomedical image segmentation. In\nstandard FCNs, only long skip connections are used to skip features from the\ncontracting path to the expanding path in order to recover spatial information\nlost during downsampling. We extend FCNs by adding short skip connections, that\nare similar to the ones introduced in residual networks, in order to build very\ndeep FCNs (of hundreds of layers). A review of the gradient flow confirms that\nfor a very deep FCN it is beneficial to have both long and short skip\nconnections. Finally, we show that a very deep FCN can achieve\nnear-to-state-of-the-art results on the EM dataset without any further\npost-processing.","url_abs":"http://arxiv.org/abs/1608.04117v2","url_pdf":"http://arxiv.org/pdf/1608.04117v2.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":"the-importance-of-skip-connections-in","repo_url":"https://github.com/lauradhatt/Interesting-Reads","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.04117","atlas_url":"https://app.syntology.ai/?focus=1608.04117","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}