{"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/bts-net-bi-directional-transfer-and-selection","title":"BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detection","arxiv_id":"2104.01784","date":"2021-04-05","proceeding":null,"authors":["Wenbo Zhang","Yao Jiang","Keren Fu","Qijun Zhao"],"abstract":"Depth information has been proved beneficial in RGB-D salient object detection (SOD). However, depth maps obtained often suffer from low quality and inaccuracy. Most existing RGB-D SOD models have no cross-modal interactions or only have unidirectional interactions from depth to RGB in their encoder stages, which may lead to inaccurate encoder features when facing low quality depth. To address this limitation, we propose to conduct progressive bi-directional interactions as early in the encoder stage, yielding a novel bi-directional transfer-and-selection network named BTS-Net, which adopts a set of bi-directional transfer-and-selection (BTS) modules to purify features during encoding. Based on the resulting robust encoder features, we also design an effective light-weight group decoder to achieve accurate final saliency prediction. Comprehensive experiments on six widely used datasets demonstrate that BTS-Net surpasses 16 latest state-of-the-art approaches in terms of four key metrics.","url_abs":"https://arxiv.org/abs/2104.01784v1","url_pdf":"https://arxiv.org/pdf/2104.01784v1.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":"bts-net-bi-directional-transfer-and-selection","repo_url":"https://github.com/zwbx/BTS-Net","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"rgb-d-salient-object-detection","task_name":"RGB-D Salient Object Detection"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"},{"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-des","task":"RGB-D Salient Object Detection","dataset":"DES","model":"BTS-Net","rank_in_archive_order":2,"of":13,"metrics":{"Average MAE":"0.018","S-Measure":"94.3","max E-Measure":"97.9","max F-Measure":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-lfsd","task":"RGB-D Salient Object Detection","dataset":"LFSD","model":"BTS-Net","rank_in_archive_order":2,"of":8,"metrics":{"Average MAE":"0.07","S-Measure":"86.7","max E-Measure":"90.6","max F-Measure":"87.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-nju2k","task":"RGB-D Salient Object Detection","dataset":"NJU2K","model":"BTS-Net","rank_in_archive_order":3,"of":27,"metrics":{"Average MAE":"0.036","S-Measure":"92.1","max E-Measure":"95.4","max F-Measure":"92.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-sip","task":"RGB-D Salient Object Detection","dataset":"SIP","model":"BTS-Net","rank_in_archive_order":3,"of":16,"metrics":{"Average MAE":"0.044","S-Measure":"89.6","max E-Measure":"93.3","max F-Measure":"90.1"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-d-salient-object-detection-on-stere","task":"RGB-D Salient Object Detection","dataset":"STERE","model":"BTS-Net","rank_in_archive_order":2,"of":14,"metrics":{"Average MAE":"0.038","S-Measure":"91.5","max E-Measure":"94.9","max F-Measure":"91.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.01784","atlas_url":"https://app.syntology.ai/?focus=2104.01784","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":"2104.01784"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.01784\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.01784"},"call":"get_concepts_for_paper(arxiv_id=\"2104.01784\")"}],"by_repo":[{"repo":"zwbx/BTS-Net","kind":"official","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":"a2aa0a6498611456b240e10851f8aeb4a0e6d3d6027231e69cdf5ee694b9d33c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}