{"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/improved-image-segmentation-via-cost","title":"Improved Image Segmentation via Cost Minimization of Multiple Hypotheses","arxiv_id":"1802.00088","date":"2018-01-31","proceeding":null,"authors":["Marc Bosch","Christopher M. Gifford","Austin G. Dress","Clare W. Lau","Jeffrey G. Skibo","Gordon A. Christie"],"abstract":"Image segmentation is an important component of many image understanding\nsystems. It aims to group pixels in a spatially and perceptually coherent\nmanner. Typically, these algorithms have a collection of parameters that\ncontrol the degree of over-segmentation produced. It still remains a challenge\nto properly select such parameters for human-like perceptual grouping. In this\nwork, we exploit the diversity of segments produced by different choices of\nparameters. We scan the segmentation parameter space and generate a collection\nof image segmentation hypotheses (from highly over-segmented to\nunder-segmented). These are fed into a cost minimization framework that\nproduces the final segmentation by selecting segments that: (1) better describe\nthe natural contours of the image, and (2) are more stable and persistent among\nall the segmentation hypotheses. We compare our algorithm's performance with\nstate-of-the-art algorithms, showing that we can achieve improved results. We\nalso show that our framework is robust to the choice of segmentation kernel\nthat produces the initial set of hypotheses.","url_abs":"http://arxiv.org/abs/1802.00088v1","url_pdf":"http://arxiv.org/pdf/1802.00088v1.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":"improved-image-segmentation-via-cost","repo_url":"https://github.com/pubgeo/cmmh_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}