{"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/scale-constrained-unsupervised-evaluation","title":"Scale-constrained Unsupervised Evaluation Method for Multi-scale Image Segmentation","arxiv_id":"1611.04850","date":"2016-11-15","proceeding":null,"authors":["Yuhang Lu","Youchuan Wan","Gang Li"],"abstract":"Unsupervised evaluation of segmentation quality is a crucial step in image\nsegmentation applications. Previous unsupervised evaluation methods usually\nlacked the adaptability to multi-scale segmentation. A scale-constrained\nevaluation method that evaluates segmentation quality according to the\nspecified target scale is proposed in this paper. First, regional saliency and\nmerging cost are employed to describe intra-region homogeneity and inter-region\nheterogeneity, respectively. Subsequently, both of them are standardized into\nequivalent spectral distances of a predefined region. Finally, by analyzing the\nrelationship between image characteristics and segmentation quality, we\nestablish the evaluation model. Experimental results show that the proposed\nmethod outperforms four commonly used unsupervised methods in multi-scale\nevaluation tasks.","url_abs":"http://arxiv.org/abs/1611.04850v1","url_pdf":"http://arxiv.org/pdf/1611.04850v1.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":"scale-constrained-unsupervised-evaluation","repo_url":"https://github.com/Rudy423/SegEvaluation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}