{"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/scene-parsing-with-global-context-embedding","title":"Scene Parsing with Global Context Embedding","arxiv_id":"1710.06507","date":"2017-10-17","proceeding":"ICCV 2017 10","authors":["Wei-Chih Hung","Yi-Hsuan Tsai","Xiaohui Shen","Zhe Lin","Kalyan Sunkavalli","Xin Lu","Ming-Hsuan Yang"],"abstract":"We present a scene parsing method that utilizes global context information\nbased on both the parametric and non- parametric models. Compared to previous\nmethods that only exploit the local relationship between objects, we train a\ncontext network based on scene similarities to generate feature representations\nfor global contexts. In addition, these learned features are utilized to\ngenerate global and spatial priors for explicit classes inference. We then\ndesign modules to embed the feature representations and the priors into the\nsegmentation network as additional global context cues. We show that the\nproposed method can eliminate false positives that are not compatible with the\nglobal context representations. Experiments on both the MIT ADE20K and PASCAL\nContext datasets show that the proposed method performs favorably against\nexisting methods.","url_abs":"http://arxiv.org/abs/1710.06507v2","url_pdf":"http://arxiv.org/pdf/1710.06507v2.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":"scene-parsing-with-global-context-embedding","repo_url":"https://github.com/hfslyc/GCPNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"scene-parsing","task_name":"Scene Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}