{"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/labelbank-revisiting-global-perspectives-for","title":"LabelBank: Revisiting Global Perspectives for Semantic Segmentation","arxiv_id":"1703.09891","date":"2017-03-29","proceeding":null,"authors":["Hexiang Hu","Zhiwei Deng","Guang-Tong Zhou","Fei Sha","Greg Mori"],"abstract":"Semantic segmentation requires a detailed labeling of image pixels by object\ncategory. Information derived from local image patches is necessary to describe\nthe detailed shape of individual objects. However, this information is\nambiguous and can result in noisy labels. Global inference of image content can\ninstead capture the general semantic concepts present. We advocate that\nholistic inference of image concepts provides valuable information for detailed\npixel labeling. We propose a generic framework to leverage holistic information\nin the form of a LabelBank for pixel-level segmentation.\n  We show the ability of our framework to improve semantic segmentation\nperformance in a variety of settings. We learn models for extracting a holistic\nLabelBank from visual cues, attributes, and/or textual descriptions. We\ndemonstrate improvements in semantic segmentation accuracy on standard datasets\nacross a range of state-of-the-art segmentation architectures and holistic\ninference approaches.","url_abs":"http://arxiv.org/abs/1703.09891v1","url_pdf":"http://arxiv.org/pdf/1703.09891v1.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":"labelbank-revisiting-global-perspectives-for","repo_url":"https://github.com/nightrome/cocostuff10k","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.09891","atlas_url":"https://app.syntology.ai/?focus=1703.09891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}