{"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/semantic-instance-segmentation-via-deep","title":"Semantic Instance Segmentation via Deep Metric Learning","arxiv_id":"1703.10277","date":"2017-03-30","proceeding":null,"authors":["Alireza Fathi","Zbigniew Wojna","Vivek Rathod","Peng Wang","Hyun Oh Song","Sergio Guadarrama","Kevin P. Murphy"],"abstract":"We propose a new method for semantic instance segmentation, by first\ncomputing how likely two pixels are to belong to the same object, and then by\ngrouping similar pixels together. Our similarity metric is based on a deep,\nfully convolutional embedding model. Our grouping method is based on selecting\nall points that are sufficiently similar to a set of \"seed points\", chosen from\na deep, fully convolutional scoring model. We show competitive results on the\nPascal VOC instance segmentation benchmark.","url_abs":"http://arxiv.org/abs/1703.10277v1","url_pdf":"http://arxiv.org/pdf/1703.10277v1.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":"semantic-instance-segmentation-via-deep","repo_url":"https://github.com/alicranck/instance-seg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"object-proposal-generation","task_name":"Object Proposal Generation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-proposal-generation-on-pascal-voc-2012","task":"Object Proposal Generation","dataset":"PASCAL VOC 2012, 60 proposals per image","model":"inst-DML","rank_in_archive_order":3,"of":3,"metrics":{"Average Recall":"0.667"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.10277","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}