{"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/iteratively-trained-interactive-segmentation","title":"Iteratively Trained Interactive Segmentation","arxiv_id":"1805.04398","date":"2018-05-11","proceeding":null,"authors":["Sabarinath Mahadevan","Paul Voigtlaender","Bastian Leibe"],"abstract":"Deep learning requires large amounts of training data to be effective. For\nthe task of object segmentation, manually labeling data is very expensive, and\nhence interactive methods are needed. Following recent approaches, we develop\nan interactive object segmentation system which uses user input in the form of\nclicks as the input to a convolutional network. While previous methods use\nheuristic click sampling strategies to emulate user clicks during training, we\npropose a new iterative training strategy. During training, we iteratively add\nclicks based on the errors of the currently predicted segmentation. We show\nthat our iterative training strategy together with additional improvements to\nthe network architecture results in improved results over the state-of-the-art.","url_abs":"http://arxiv.org/abs/1805.04398v1","url_pdf":"http://arxiv.org/pdf/1805.04398v1.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":"iteratively-trained-interactive-segmentation","repo_url":"https://github.com/sabarim/itis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"interactive-segmentation","task_name":"Interactive Segmentation"},{"task_slug":"object","task_name":"Object"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.04398","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}