{"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/enhanced-alignment-measure-for-binary","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","arxiv_id":"1805.10421","date":"2018-05-26","proceeding":null,"authors":["Deng-Ping Fan","Cheng Gong","Yang Cao","Bo Ren","Ming-Ming Cheng","Ali Borji"],"abstract":"The existing binary foreground map (FM) measures to address various types of\nerrors in either pixel-wise or structural ways. These measures consider\npixel-level match or image-level information independently, while cognitive\nvision studies have shown that human vision is highly sensitive to both global\ninformation and local details in scenes. In this paper, we take a detailed look\nat current binary FM evaluation measures and propose a novel and effective\nE-measure (Enhanced-alignment measure). Our measure combines local pixel values\nwith the image-level mean value in one term, jointly capturing image-level\nstatistics and local pixel matching information. We demonstrate the superiority\nof our measure over the available measures on 4 popular datasets via 5\nmeta-measures, including ranking models for applications, demoting generic,\nrandom Gaussian noise maps, ground-truth switch, as well as human judgments. We\nfind large improvements in almost all the meta-measures. For instance, in terms\nof application ranking, we observe improvementrangingfrom9.08% to 19.65%\ncompared with other popular measures.","url_abs":"http://arxiv.org/abs/1805.10421v2","url_pdf":"http://arxiv.org/pdf/1805.10421v2.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":"enhanced-alignment-measure-for-binary","repo_url":"https://github.com/DengPingFan/E-measure","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"enhanced-alignment-measure-for-binary","repo_url":"https://github.com/Mehrdad-Noori/Saliency-Evaluation-Toolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10421","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}