{"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/salient-objects-in-clutter-bringing-salient","title":"Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground","arxiv_id":"1803.06091","date":"2018-03-16","proceeding":"ECCV 2018 9","authors":["Deng-Ping Fan","Ming-Ming Cheng","Jiang-Jiang Liu","Shang-Hua Gao","Qibin Hou","Ali Borji"],"abstract":"We provide a comprehensive evaluation of salient object detection (SOD)\nmodels. Our analysis identifies a serious design bias of existing SOD datasets\nwhich assumes that each image contains at least one clearly outstanding salient\nobject in low clutter. The design bias has led to a saturated high performance\nfor state-of-the-art SOD models when evaluated on existing datasets. The\nmodels, however, still perform far from being satisfactory when applied to\nreal-world daily scenes. Based on our analyses, we first identify 7 crucial\naspects that a comprehensive and balanced dataset should fulfill. Then, we\npropose a new high quality dataset and update the previous saliency benchmark.\nSpecifically, our SOC (Salient Objects in Clutter) dataset, includes images\nwith salient and non-salient objects from daily object categories. Beyond\nobject category annotations, each salient image is accompanied by attributes\nthat reflect common challenges in real-world scenes. Finally, we report\nattribute-based performance assessment on our dataset.","url_abs":"http://arxiv.org/abs/1803.06091v2","url_pdf":"http://arxiv.org/pdf/1803.06091v2.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection","task_name":"RGB Salient Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"soc","name":"SOC","full_name":"Salient Objects in Clutter"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.06091","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}