{"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/fast-interactive-object-annotation-with-curve","title":"Fast Interactive Object Annotation with Curve-GCN","arxiv_id":"1903.06874","date":"2019-03-16","proceeding":"CVPR 2019 6","authors":["Huan Ling","Jun Gao","Amlan Kar","Wenzheng Chen","Sanja Fidler"],"abstract":"Manually labeling objects by tracing their boundaries is a laborious process.\nIn Polygon-RNN++ the authors proposed Polygon-RNN that produces polygonal\nannotations in a recurrent manner using a CNN-RNN architecture, allowing\ninteractive correction via humans-in-the-loop. We propose a new framework that\nalleviates the sequential nature of Polygon-RNN, by predicting all vertices\nsimultaneously using a Graph Convolutional Network (GCN). Our model is trained\nend-to-end. It supports object annotation by either polygons or splines,\nfacilitating labeling efficiency for both line-based and curved objects. We\nshow that Curve-GCN outperforms all existing approaches in automatic mode,\nincluding the powerful PSP-DeepLab and is significantly more efficient in\ninteractive mode than Polygon-RNN++. Our model runs at 29.3ms in automatic, and\n2.6ms in interactive mode, making it 10x and 100x faster than Polygon-RNN++.","url_abs":"http://arxiv.org/abs/1903.06874v1","url_pdf":"http://arxiv.org/pdf/1903.06874v1.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":"fast-interactive-object-annotation-with-curve","repo_url":"https://github.com/fidler-lab/curve-gcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"fast-interactive-object-annotation-with-curve","repo_url":"https://github.com/mng827/curve-gcn-cardiac-mr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.06874","atlas_url":"https://app.syntology.ai/?focus=1903.06874","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}