{"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/a-weakly-supervised-learning-framework-for","title":"A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels","arxiv_id":"2209.02957","date":"2022-09-07","proceeding":null,"authors":["Runmin Cong","Qi Qin","Chen Zhang","Qiuping Jiang","Shiqi Wang","Yao Zhao","Sam Kwong"],"abstract":"Fully-supervised salient object detection (SOD) methods have made great progress, but such methods often rely on a large number of pixel-level annotations, which are time-consuming and labour-intensive. In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels. To address the issues of label noise and quantity imbalance in this task, we design a new pipeline framework with three sophisticated training strategies. In terms of model framework, we decouple the task into label refinement sub-task and salient object detection sub-task, which cooperate with each other and train alternately. Specifically, the R-Net is designed as a two-stream encoder-decoder model equipped with Blender with Guidance and Aggregation Mechanisms (BGA), aiming to rectify the coarse labels for more reliable pseudo-labels, while the S-Net is a replaceable SOD network supervised by the pseudo labels generated by the current R-Net. Note that, we only need to use the trained S-Net for testing. Moreover, in order to guarantee the effectiveness and efficiency of network training, we design three training strategies, including alternate iteration mechanism, group-wise incremental mechanism, and credibility verification mechanism. Experiments on five SOD benchmarks show that our method achieves competitive performance against weakly-supervised/unsupervised methods both qualitatively and quantitatively.","url_abs":"https://arxiv.org/abs/2209.02957v1","url_pdf":"https://arxiv.org/pdf/2209.02957v1.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":"a-weakly-supervised-learning-framework-for","repo_url":"https://github.com/rmcong/Hybrid-Label-SOD_TCSVT2022","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"a-weakly-supervised-learning-framework-for","repo_url":"https://gitee.com/dakerqinqi/wslnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"a-weakly-supervised-learning-framework-for","repo_url":"https://github.com/2023-MindSpore-4/Code4/tree/main/wslnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"roipool","method_name":"RoIPool"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/salient-object-detection-on-duts-te","task":"RGB Salient Object Detection","dataset":"DUTS-TE","model":"HybridSOD","rank_in_archive_order":16,"of":31,"metrics":{"MAE":"0.05","S-Measure":"0.837"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-ecssd","task":"RGB Salient Object Detection","dataset":"ECSSD","model":"HybridSOD","rank_in_archive_order":7,"of":14,"metrics":{"F-Score":"0.899","MAE":"0.051","S-Measure":"0.886"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is","task":"RGB Salient Object Detection","dataset":"HKU-IS","model":"HybridSOD","rank_in_archive_order":7,"of":14,"metrics":{"F-Score":"0.892","MAE":"0.038","S-Measure":"0.887"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-pascal-s","task":"RGB Salient Object Detection","dataset":"PASCAL-S","model":"HybridSOD","rank_in_archive_order":6,"of":13,"metrics":{"F-Score":"0.827","MAE":"0.076","S-Measure":"0.828"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}