{"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/revisiting-quantization-error-in-face","title":"Revisiting Quantization Error in Face Alignment","arxiv_id":null,"date":"2021-09-13","proceeding":"ICCV Workshop 2021 9","authors":["Xing Lan","Qinghao Hu","Jian Cheng"],"abstract":"Recently, heatmap regression models have become the mainstream in locating facial landmarks. To keep com- putation affordable and reduce memory usage, the whole procedure involves downsampling from the raw image to the output heatmap. However, how much impact will the quantization error introduced by downsampling bring? The problem is hardly systematically investigated among previ- ous works. This work fills the blank and we are the first to quantitatively analyze the negative gain. The statistical re- sults show the NME generated by quantization error is even larger than 1/3 of the SOTA item, which is a serious obsta- cle for making a new breakthrough in face alignment. To compensate for the impact of quantization effect, we pro- pose a novel method, called Heatmap In Heatmap (HIH), which leverages two categories of heatmaps as label repre- sentation to encode the coordinate. And in HIH, the range of one heatmap represents a pixel of the other category of heatmap. Also, we even combine the face alignment with solutions of other fields to make a comparison. Extensive experiments on various benchmarks show the feasibility of HIH and superior performance than other solutions. More- over, the mean error reaches to 4.18 on WFLW, which ex- ceeds SOTA a lot.","url_abs":"https://openaccess.thecvf.com/content/ICCV2021W/MFR/html/Lan_Revisting_Quantization_Error_in_Face_Alignment_ICCVW_2021_paper.html","url_pdf":"https://openaccess.thecvf.com/content/ICCV2021W/MFR/papers/Lan_Revisting_Quantization_Error_in_Face_Alignment_ICCVW_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":"face-alignment","task_name":"Face Alignment"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-cofw","task":"Face Alignment","dataset":"COFW","model":"HIH w. MSE(2 stack)","rank_in_archive_order":8,"of":28,"metrics":{"NME (inter-ocular)":"3.28%"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-wflw","task":"Face Alignment","dataset":"WFLW","model":"HIH w. MSE(2-stack)","rank_in_archive_order":11,"of":36,"metrics":{"AUC@10 (inter-ocular)":"59.7","FR@10 (inter-ocular)":"2.84","NME (inter-ocular)":"4.18"},"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":"322c369c92dfcd7467e576980c5bb11f26af08e5e472b0f3a35a6e5babdd0a3a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}