{"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/semi-supervised-video-salient-object","title":"Semi-Supervised Video Salient Object Detection Using Pseudo-Labels","arxiv_id":"1908.04051","date":"2019-08-12","proceeding":"ICCV 2019 10","authors":["Pengxiang Yan","Guanbin Li","Yuan Xie","Zhen Li","Chuan Wang","Tianshui Chen","Liang Lin"],"abstract":"Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods. However, existing data-driven approaches heavily rely on a large quantity of pixel-wise annotated video frames to deliver such promising results. In this paper, we address the semi-supervised video salient object detection task using pseudo-labels. Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module. Based on the same refinement network and motion information in terms of optical flow, we further propose a novel method for generating pixel-level pseudo-labels from sparsely annotated frames. By utilizing the generated pseudo-labels together with a part of manual annotations, our video saliency detector learns spatial and temporal cues for both contrast inference and coherence enhancement, thus producing accurate saliency maps. Experimental results demonstrate that our proposed semi-supervised method even greatly outperforms all the state-of-the-art fully supervised methods across three public benchmarks of VOS, DAVIS, and FBMS.","url_abs":"https://arxiv.org/abs/1908.04051v2","url_pdf":"https://arxiv.org/pdf/1908.04051v2.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":"semi-supervised-video-salient-object","repo_url":"https://github.com/Kinpzz/RCRNet-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-salient-object-detection","task_name":"Video Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-salient-object-detection-on-davis-2016","task":"Video Salient Object Detection","dataset":"DAVIS-2016","model":"RCRNet+NER","rank_in_archive_order":5,"of":11,"metrics":{"AVERAGE MAE":"0.028","MAX F-MEASURE":"0.859","S-Measure":"0.884"},"uses_additional_data":true},{"leaderboard":"/sota/video-salient-object-detection-on-fbms-59","task":"Video Salient Object Detection","dataset":"FBMS-59","model":"RCRNet+NER","rank_in_archive_order":4,"of":16,"metrics":{"AVERAGE MAE":"0.054","MAX F-MEASURE":"0.861","S-Measure":"0.870"},"uses_additional_data":true},{"leaderboard":"/sota/video-salient-object-detection-on-vos-t","task":"Video Salient Object Detection","dataset":"VOS-T","model":"RCRNet+NER","rank_in_archive_order":1,"of":9,"metrics":{"Average MAE":"0.049","S-Measure":"0.872","max E-measure":"0.856"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.04051","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}