{"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/convolutional-oriented-boundaries","title":"Convolutional Oriented Boundaries","arxiv_id":"1608.02755","date":"2016-08-09","proceeding":null,"authors":["Kevis-Kokitsi Maninis","Jordi Pont-Tuset","Pablo Arbeláez","Luc van Gool"],"abstract":"We present Convolutional Oriented Boundaries (COB), which produces multiscale\noriented contours and region hierarchies starting from generic image\nclassification Convolutional Neural Networks (CNNs). COB is computationally\nefficient, because it requires a single CNN forward pass for contour detection\nand it uses a novel sparse boundary representation for hierarchical\nsegmentation; it gives a significant leap in performance over the\nstate-of-the-art, and it generalizes very well to unseen categories and\ndatasets. Particularly, we show that learning to estimate not only contour\nstrength but also orientation provides more accurate results. We perform\nextensive experiments on BSDS, PASCAL Context, PASCAL Segmentation, and\nMS-COCO, showing that COB provides state-of-the-art contours, region\nhierarchies, and object proposals in all datasets.","url_abs":"http://arxiv.org/abs/1608.02755v1","url_pdf":"http://arxiv.org/pdf/1608.02755v1.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":"convolutional-oriented-boundaries","repo_url":"https://github.com/kmaninis/COB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"contour-detection","task_name":"Contour Detection"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"}],"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}