{"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/image-segmentation-using-sparse-subset","title":"Image Segmentation using Sparse Subset Selection","arxiv_id":"1804.02721","date":"2018-04-08","proceeding":null,"authors":["Fariba Zohrizadeh","Mohsen Kheirandishfard","Farhad Kamangar"],"abstract":"In this paper, we present a new image segmentation method based on the\nconcept of sparse subset selection. Starting with an over-segmentation, we\nadopt local spectral histogram features to encode the visual information of the\nsmall segments into high-dimensional vectors, called superpixel features. Then,\nthe superpixel features are fed into a novel convex model which efficiently\nleverages the features to group the superpixels into a proper number of\ncoherent regions. Our model automatically determines the optimal number of\ncoherent regions and superpixels assignment to shape final segments. To solve\nour model, we propose a numerical algorithm based on the alternating direction\nmethod of multipliers (ADMM), whose iterations consist of two highly\nparallelizable sub-problems. We show each sub-problem enjoys closed-form\nsolution which makes the ADMM iterations computationally very efficient.\nExtensive experiments on benchmark image segmentation datasets demonstrate that\nour proposed method in combination with an over-segmentation can provide high\nquality and competitive results compared to the existing state-of-the-art\nmethods.","url_abs":"http://arxiv.org/abs/1804.02721v1","url_pdf":"http://arxiv.org/pdf/1804.02721v1.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":"image-segmentation-using-sparse-subset","repo_url":"https://github.com/mohsenkheirandishfard/IS4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"superpixels","task_name":"Superpixels"}],"methods":[{"method_slug":"admm","method_name":"ADMM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}