{"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/siamese-network-for-rgb-d-salient-object","title":"Siamese Network for RGB-D Salient Object Detection and Beyond","arxiv_id":"2008.12134","date":"2020-08-26","proceeding":null,"authors":["Keren Fu","Deng-Ping Fan","Ge-Peng Ji","Qijun Zhao","Jianbing Shen","Ce Zhu"],"abstract":"Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture. In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of ~2.0% (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task.","url_abs":"https://arxiv.org/abs/2008.12134v2","url_pdf":"https://arxiv.org/pdf/2008.12134v2.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":"siamese-network-for-rgb-d-salient-object","repo_url":"https://github.com/kerenfu/JLDCF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"siamese-network-for-rgb-d-salient-object","repo_url":"https://github.com/taozh2017/RGBD-SODsurvey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"JL-DCF*","rank_in_archive_order":6,"of":13,"metrics":{"Average MAE":"0.021","S-Measure":"93.6","max E-Measure":"97.5","max F-Measure":"92.9"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"JL-DCF*","rank_in_archive_order":8,"of":27,"metrics":{"Average MAE":"0.040","S-Measure":"91.1","max E-Measure":"94.8","max F-Measure":"91.3"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"JL-DCF*","rank_in_archive_order":6,"of":14,"metrics":{"Average MAE":"0.023","S-Measure":"92.6","max E-Measure":"96.4","max F-Measure":"91.7"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"JL-DCF*","rank_in_archive_order":6,"of":16,"metrics":{"Average MAE":"0.046","S-Measure":"89.2","max E-Measure":"94.9","max F-Measure":"90.0"},"uses_additional_data":true},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"JL-DCF*","rank_in_archive_order":3,"of":14,"metrics":{"Average MAE":"0.039","S-Measure":"91.1","max E-Measure":"94.9","max F-Measure":"90.7"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2008.12134","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}