{"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/synthref-generation-of-synthetic-referring","title":"SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation","arxiv_id":"2106.04403","date":"2021-06-08","proceeding":null,"authors":["Ioannis Kazakos","Carles Ventura","Miriam Bellver","Carina Silberer","Xavier Giro-i-Nieto"],"abstract":"Recent advances in deep learning have brought significant progress in visual grounding tasks such as language-guided video object segmentation. However, collecting large datasets for these tasks is expensive in terms of annotation time, which represents a bottleneck. To this end, we propose a novel method, namely SynthRef, for generating synthetic referring expressions for target objects in an image (or video frame), and we also present and disseminate the first large-scale dataset with synthetic referring expressions for video object segmentation. Our experiments demonstrate that by training with our synthetic referring expressions one can improve the ability of a model to generalize across different datasets, without any additional annotation cost. Moreover, our formulation allows its application to any object detection or segmentation dataset.","url_abs":"https://arxiv.org/abs/2106.04403v2","url_pdf":"https://arxiv.org/pdf/2106.04403v2.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":"synthref-generation-of-synthetic-referring","repo_url":"https://github.com/imatge-upc/synthref","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"synthref-generation-of-synthetic-referring","repo_url":"https://github.com/miriambellver/refvos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-davis","task":"Referring Expression Segmentation","dataset":"DAVIS 2017 (val)","model":"RefVOS + SynthRef-YouTube-VIS","rank_in_archive_order":12,"of":18,"metrics":{"J&F 1st frame":"45.3","J&F Full video":"44.8"},"uses_additional_data":true},{"leaderboard":"/sota/referring-expression-segmentation-on-davis","task":"Referring Expression Segmentation","dataset":"DAVIS 2017 (val)","model":"RefVOS","rank_in_archive_order":13,"of":18,"metrics":{"J&F 1st frame":"45.1"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refer","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS","model":"RefVOS-Human REs","rank_in_archive_order":1,"of":2,"metrics":{"Mean IoU":"39.5","Precision@0.5":"38.6","Precision@0.9":"6.9"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refer","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS","model":"RefVOS-Synthetic REs","rank_in_archive_order":2,"of":2,"metrics":{"Mean IoU":"35.0","Precision@0.5":"32.3","Precision@0.9":"1.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.04403","atlas_url":"https://app.syntology.ai/?focus=2106.04403","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}