{"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/rgbd-salient-object-detection-via-deep-fusion","title":"RGBD Salient Object Detection via Deep Fusion","arxiv_id":"1607.03333","date":"2016-07-12","proceeding":null,"authors":["Liangqiong Qu","Shengfeng He","Jiawei Zhang","Jiandong Tian","Yandong Tang","Qingxiong Yang"],"abstract":"Numerous efforts have been made to design different low level saliency cues\nfor the RGBD saliency detection, such as color or depth contrast features,\nbackground and color compactness priors. However, how these saliency cues\ninteract with each other and how to incorporate these low level saliency cues\neffectively to generate a master saliency map remain a challenging problem. In\nthis paper, we design a new convolutional neural network (CNN) to fuse\ndifferent low level saliency cues into hierarchical features for automatically\ndetecting salient objects in RGBD images. In contrast to the existing works\nthat directly feed raw image pixels to the CNN, the proposed method takes\nadvantage of the knowledge in traditional saliency detection by adopting\nvarious meaningful and well-designed saliency feature vectors as input. This\ncan guide the training of CNN towards detecting salient object more effectively\ndue to the reduced learning ambiguity. We then integrate a Laplacian\npropagation framework with the learned CNN to extract a spatially consistent\nsaliency map by exploiting the intrinsic structure of the input image.\nExtensive quantitative and qualitative experimental evaluations on three\ndatasets demonstrate that the proposed method consistently outperforms\nstate-of-the-art methods.","url_abs":"http://arxiv.org/abs/1607.03333v1","url_pdf":"http://arxiv.org/pdf/1607.03333v1.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":"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":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"LHM","rank_in_archive_order":26,"of":27,"metrics":{"Average MAE":"0.205","S-Measure":"51.4","max E-Measure":"72.4","max F-Measure":"63.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1607.03333","atlas_url":"https://app.syntology.ai/?focus=1607.03333","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}