{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/uncertainty-inspired-rgb-d-saliency-detection","title":"Uncertainty Inspired RGB-D Saliency Detection","arxiv_id":"2009.03075","date":"2020-09-07","proceeding":null,"authors":["Jing Zhang","Deng-Ping Fan","Yuchao Dai","Saeed Anwar","Fatemeh Saleh","Sadegh Aliakbarian","Nick Barnes"],"abstract":"We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet.","url_abs":"https://arxiv.org/abs/2009.03075v1","url_pdf":"https://arxiv.org/pdf/2009.03075v1.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":"uncertainty-inspired-rgb-d-saliency-detection","repo_url":"https://github.com/JingZhang617/UCNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"uncertainty-inspired-rgb-d-saliency-detection","repo_url":"https://github.com/DengPingFan/SOC-DataAug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"uncertainty-inspired-rgb-d-saliency-detection","repo_url":"https://github.com/DengPingFan/S-measure","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"uncertainty-inspired-rgb-d-saliency-detection","repo_url":"https://github.com/taozh2017/RGBD-SODsurvey","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/salient-object-detection-on-dut-omron","task":"RGB Salient Object Detection","dataset":"DUT-OMRON","model":"UCNet-ABP","rank_in_archive_order":10,"of":18,"metrics":{"MAE":"0.050","S-Measure":"0.843"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-dut-omron","task":"RGB Salient Object Detection","dataset":"DUT-OMRON","model":"UCNet-CVAE","rank_in_archive_order":11,"of":18,"metrics":{"MAE":"0.051","S-Measure":"0.839"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-duts-te","task":"RGB Salient Object Detection","dataset":"DUTS-TE","model":"UCNet-ABP","rank_in_archive_order":10,"of":31,"metrics":{"MAE":"0.034","S-Measure":"0.890","mean E-Measure":"0.931","mean F-Measure":"0.864"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-duts-te","task":"RGB Salient Object Detection","dataset":"DUTS-TE","model":"UCNet-CVAE","rank_in_archive_order":11,"of":31,"metrics":{"MAE":"0.034","S-Measure":"0.888","mean E-Measure":"0.927","mean F-Measure":"0.860"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-ecssd","task":"RGB Salient Object Detection","dataset":"ECSSD","model":"UCNet-CVAE","rank_in_archive_order":6,"of":14,"metrics":{"MAE":"0.035","S-Measure":"0.921"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is","task":"RGB Salient Object Detection","dataset":"HKU-IS","model":"UCNet-CVAE","rank_in_archive_order":5,"of":14,"metrics":{"MAE":"0.026","S-Measure":"0.921"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-hku-is","task":"RGB Salient Object Detection","dataset":"HKU-IS","model":"UCNet-ABP","rank_in_archive_order":6,"of":14,"metrics":{"MAE":"0.027","S-Measure":"0.917"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-soc","task":"RGB Salient Object Detection","dataset":"SOC","model":"UCNet-CVAE","rank_in_archive_order":1,"of":7,"metrics":{"Average MAE":"0.089","S-Measure":"0.849","mean E-Measure":"0.872"},"uses_additional_data":false},{"leaderboard":"/sota/salient-object-detection-on-soc","task":"RGB Salient Object Detection","dataset":"SOC","model":"UCNet-APB","rank_in_archive_order":2,"of":7,"metrics":{"Average MAE":"0.091","S-Measure":"0.842","mean E-Measure":"0.868"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"UCNet-ABP","rank_in_archive_order":3,"of":13,"metrics":{"Average MAE":"0.016","S-Measure":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"UCNet-CVAE","rank_in_archive_order":5,"of":13,"metrics":{"Average MAE":"0.016","S-Measure":"93.7"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-lfsd","task":"RGB-D Salient Object Detection","dataset":"LFSD","model":"UCNet-CVAE","rank_in_archive_order":1,"of":8,"metrics":{"Average MAE":"0.065","S-Measure":"86.8"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-lfsd","task":"RGB-D Salient Object Detection","dataset":"LFSD","model":"UCNet-ABP","rank_in_archive_order":3,"of":8,"metrics":{"Average MAE":"0.065","S-Measure":"86.6"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"UCNet-CVAE","rank_in_archive_order":12,"of":27,"metrics":{"Average MAE":"0.039","S-Measure":"90.2"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"UCNet-ABP","rank_in_archive_order":14,"of":27,"metrics":{"Average MAE":"0.039","S-Measure":"90.0"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"UCNet-ABP","rank_in_archive_order":10,"of":14,"metrics":{"Average MAE":"0.024","S-Measure":"91.9"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nlpr","task":"RGB-D Salient Object Detection","dataset":"NLPR","model":"UCNet-CAVE","rank_in_archive_order":11,"of":14,"metrics":{"Average MAE":"0.025","S-Measure":"91.7"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"UCNet-CVAE","rank_in_archive_order":7,"of":16,"metrics":{"Average MAE":"0.045","S-Measure":"88.3"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"UCNet-ABP","rank_in_archive_order":11,"of":16,"metrics":{"Average MAE":"0.049","S-Measure":"87.6"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"UCNet-ABP","rank_in_archive_order":9,"of":14,"metrics":{"Average MAE":"0.037","S-Measure":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"UCNet-CVAE","rank_in_archive_order":13,"of":14,"metrics":{"Average MAE":"0.039","S-Measure":"89.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.03075","atlas_url":"https://app.syntology.ai/?focus=2009.03075","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2009.03075"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2009.03075\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2009.03075"},"call":"get_concepts_for_paper(arxiv_id=\"2009.03075\")"}],"by_repo":[{"repo":"JingZhang617/UCNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DengPingFan/SOC-DataAug","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"DengPingFan/S-measure","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"taozh2017/RGBD-SODsurvey","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f3851a123f40da9d55a54faeac582221e632b63da56359fa82cc617870f176ba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}