{"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/reformulating-level-sets-as-deep-recurrent","title":"Reformulating Level Sets as Deep Recurrent Neural Network Approach to Semantic Segmentation","arxiv_id":"1704.03593","date":"2017-04-12","proceeding":null,"authors":["Ngan Le","Kha Gia Quach","Khoa Luu","Marios Savvides","Chenchen Zhu"],"abstract":"Variational Level Set (LS) has been a widely used method in medical\nsegmentation. However, it is limited when dealing with multi-instance objects\nin the real world. In addition, its segmentation results are quite sensitive to\ninitial settings and highly depend on the number of iterations. To address\nthese issues and boost the classic variational LS methods to a new level of the\nlearnable deep learning approaches, we propose a novel definition of contour\nevolution named Recurrent Level Set (RLS)} to employ Gated Recurrent Unit under\nthe energy minimization of a variational LS functional. The curve deformation\nprocess in RLS is formed as a hidden state evolution procedure and updated by\nminimizing an energy functional composed of fitting forces and contour length.\nBy sharing the convolutional features in a fully end-to-end trainable\nframework, we extend RLS to Contextual RLS (CRLS) to address semantic\nsegmentation in the wild. The experimental results have shown that our proposed\nRLS improves both computational time and segmentation accuracy against the\nclassic variations LS-based method, whereas the fully end-to-end system CRLS\nachieves competitive performance compared to the state-of-the-art semantic\nsegmentation approaches.","url_abs":"http://arxiv.org/abs/1704.03593v1","url_pdf":"http://arxiv.org/pdf/1704.03593v1.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":"reformulating-level-sets-as-deep-recurrent","repo_url":"https://github.com/lthngan/Reformulating-Level-Sets-as-Deep-Recurrent-Neural-Network-Approach-to-Semantic-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.03593","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}