{"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/mitigating-intensity-bias-in-shadow-detection","title":"Mitigating Intensity Bias in Shadow Detection via Feature Decomposition and Reweighting","arxiv_id":null,"date":"2021-01-01","proceeding":"ICCV 2021 10","authors":["Lei Zhu","Ke Xu","Zhanghan Ke","Rynson W.H. Lau"],"abstract":"    While CNNs achieved remarkable progress in shadow detection, they tend to make mistakes in dark non-shadow regions and relatively bright shadow regions. They are also susceptible to brightness change. These two phenomenons reveal that deep shadow detectors heavily depend on the intensity cue, which we refer to as intensity bias. In this paper, we propose a novel feature decomposition and reweighting scheme to mitigate this intensity bias, in which multi-level integrated features are decomposed into intensity-variant and intensity-invariant components through self-supervision. By reweighting these two types of features, our method can reallocate the attention to the corresponding latent semantics and achieves balanced exploitation of them. Extensive experiments on three popular datasets show that the proposed method outperforms state-of-the-art shadow detectors.    ","url_abs":"http://openaccess.thecvf.com//content/ICCV2021/html/Zhu_Mitigating_Intensity_Bias_in_Shadow_Detection_via_Feature_Decomposition_and_ICCV_2021_paper.html","url_pdf":"http://openaccess.thecvf.com//content/ICCV2021/papers/Zhu_Mitigating_Intensity_Bias_in_Shadow_Detection_via_Feature_Decomposition_and_ICCV_2021_paper.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":"shadow-detection","task_name":"Shadow Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/shadow-detection-on-cuhk-shadow","task":"Shadow Detection","dataset":"CUHK-Shadow","model":"FDRNet (ICCV 2021) (512x512)","rank_in_archive_order":1,"of":16,"metrics":{"BER":"6.58"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-cuhk-shadow","task":"Shadow Detection","dataset":"CUHK-Shadow","model":"ECA (MM 2021) (512x512)","rank_in_archive_order":4,"of":16,"metrics":{"BER":"7.99"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-cuhk-shadow","task":"Shadow Detection","dataset":"CUHK-Shadow","model":"ECA (MM 2021) (256x256)","rank_in_archive_order":7,"of":16,"metrics":{"BER":"8.58"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-cuhk-shadow","task":"Shadow Detection","dataset":"CUHK-Shadow","model":"FDRNet (ICCV 2021) (256x256)","rank_in_archive_order":16,"of":16,"metrics":{"BER":"14.39"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-sbu","task":"Shadow Detection","dataset":"SBU / SBU-Refine","model":"FDRNet (ICCV 2021) (512x512)","rank_in_archive_order":5,"of":16,"metrics":{"BER":"5.39"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-sbu","task":"Shadow Detection","dataset":"SBU / SBU-Refine","model":"FDRNet (ICCV 2021) (256x256)","rank_in_archive_order":7,"of":16,"metrics":{"BER":"5.64"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-sbu","task":"Shadow Detection","dataset":"SBU / SBU-Refine","model":"ECA (MM 2021) (256x256)","rank_in_archive_order":14,"of":16,"metrics":{"BER":"7.08"},"uses_additional_data":false},{"leaderboard":"/sota/shadow-detection-on-sbu","task":"Shadow Detection","dataset":"SBU / SBU-Refine","model":"ECA (MM 2021) (512x512)","rank_in_archive_order":16,"of":16,"metrics":{"BER":"7.52"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5ca5e25b19298d9e2147de4dd66b180a678d85c5fa301e98916aae7aade121e5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}