{"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/gradient-induced-co-saliency-detection","title":"Gradient-Induced Co-Saliency Detection","arxiv_id":"2004.13364","date":"2020-04-28","proceeding":"ECCV 2020 8","authors":["Zhao Zhang","Wenda Jin","Jun Xu","Ming-Ming Cheng"],"abstract":"Co-saliency detection (Co-SOD) aims to segment the common salient foreground in a group of relevant images. In this paper, inspired by human behavior, we propose a gradient-induced co-saliency detection (GICD) method. We first abstract a consensus representation for the grouped images in the embedding space; then, by comparing the single image with consensus representation, we utilize the feedback gradient information to induce more attention to the discriminative co-salient features. In addition, due to the lack of Co-SOD training data, we design a jigsaw training strategy, with which Co-SOD networks can be trained on general saliency datasets without extra pixel-level annotations. To evaluate the performance of Co-SOD methods on discovering the co-salient object among multiple foregrounds, we construct a challenging CoCA dataset, where each image contains at least one extraneous foreground along with the co-salient object. Experiments demonstrate that our GICD achieves state-of-the-art performance. Our codes and dataset are available at https://mmcheng.net/gicd/.","url_abs":"https://arxiv.org/abs/2004.13364v3","url_pdf":"https://arxiv.org/pdf/2004.13364v3.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":"gradient-induced-co-saliency-detection","repo_url":"https://github.com/zzhanghub/gicd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"co-saliency-detection","task_name":"Co-Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[{"method_slug":"jigsaw","method_name":"Jigsaw"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/co-salient-object-detection-on-coca","task":"Co-Salient Object Detection","dataset":"CoCA","model":"GICD","rank_in_archive_order":8,"of":10,"metrics":{"MAE":"0.126","Mean F-measure":"0.504","S-measure":"0.658","max E-measure":"0.715","max F-measure":"0.513","mean E-measure":"0.701"},"uses_additional_data":false},{"leaderboard":"/sota/co-salient-object-detection-on-cosod3k","task":"Co-Salient Object Detection","dataset":"CoSOD3k","model":"GICD","rank_in_archive_order":7,"of":10,"metrics":{"MAE":"0.079","S-measure":"0.797","max E-measure":"0.848","max F-measure":"0.770","mean E-measure":"0.845","mean F-measure":"0.763"},"uses_additional_data":false},{"leaderboard":"/sota/co-salient-object-detection-on-cosal2015","task":"Co-Salient Object Detection","dataset":"CoSal2015","model":"GICD","rank_in_archive_order":7,"of":10,"metrics":{"MAE":"0.071","S-measure":"0.844","max E-measure":"0.887","max F-measure":"0.844","mean E-measure":"0.883","mean F-measure":"0.835"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.13364","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}