{"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-hierarchical-merge","title":"Image Segmentation Using Hierarchical Merge Tree","arxiv_id":"1505.06389","date":"2015-05-24","proceeding":null,"authors":["Ting Liu","Mojtaba Seyedhosseini","Tolga Tasdizen"],"abstract":"This paper investigates one of the most fundamental computer vision problems:\nimage segmentation. We propose a supervised hierarchical approach to\nobject-independent image segmentation. Starting with over-segmenting\nsuperpixels, we use a tree structure to represent the hierarchy of region\nmerging, by which we reduce the problem of segmenting image regions to finding\na set of label assignment to tree nodes. We formulate the tree structure as a\nconstrained conditional model to associate region merging with likelihoods\npredicted using an ensemble boundary classifier. Final segmentations can then\nbe inferred by finding globally optimal solutions to the model efficiently. We\nalso present an iterative training and testing algorithm that generates various\ntree structures and combines them to emphasize accurate boundaries by\nsegmentation accumulation. Experiment results and comparisons with other very\nrecent methods on six public data sets demonstrate that our approach achieves\nthe state-of-the-art region accuracy and is very competitive in image\nsegmentation without semantic priors.","url_abs":"http://arxiv.org/abs/1505.06389v3","url_pdf":"http://arxiv.org/pdf/1505.06389v3.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-hierarchical-merge","repo_url":"https://github.com/tingliu/glia","is_official":1,"mentioned_in_paper":1,"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}