{"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/collaborative-annotation-of-semantic-objects","title":"Collaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions","arxiv_id":"1806.10269","date":"2018-06-27","proceeding":null,"authors":["Lishi Zhang","Chenghan Fu","Jia Li"],"abstract":"Per-pixel masks of semantic objects are very useful in many applications,\nwhich, however, are tedious to be annotated. In this paper, we propose a\nhuman-agent collaborative annotation approach that can efficiently generate\nper-pixel masks of semantic objects in tagged images with multi-granularity\nsupervisions. Given a set of tagged image, a computer agent is first\ndynamically generated to roughly localize the semantic objects described by the\ntag. The agent first extracts massive object proposals from an image and then\ninfer the tag-related ones under the weak and strong supervisions from\nlinguistically and visually similar images and previously annotated object\nmasks. By representing such supervisions by over-complete dictionaries, the\ntag-related object proposals can pop-out according to their sparse coding\nlength, which are then converted to superpixels with binary labels. After that,\nhuman annotators participate in the annotation process by flipping labels and\ndividing superpixels with mouse clicks, which are used as click supervisions\nthat teach the agent to recover false positives/negatives in processing images\nwith the same tags. Experimental results show that our approach can facilitate\nthe annotation process and generate object masks that are highly consistent\nwith those generated by the LabelMe toolbox.","url_abs":"http://arxiv.org/abs/1806.10269v1","url_pdf":"http://arxiv.org/pdf/1806.10269v1.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":"collaborative-annotation-of-semantic-objects","repo_url":"https://github.com/yuxi120407/transfer_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"superpixels","task_name":"Superpixels"},{"task_slug":"tag","task_name":"TAG"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}