{"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/subpixel-heatmap-regression-for-facial","title":"Subpixel Heatmap Regression for Facial Landmark Localization","arxiv_id":"2111.02360","date":"2021-11-03","proceeding":null,"authors":["Adrian Bulat","Enrique Sanchez","Georgios Tzimiropoulos"],"abstract":"Deep Learning models based on heatmap regression have revolutionized the task of facial landmark localization with existing models working robustly under large poses, non-uniform illumination and shadows, occlusions and self-occlusions, low resolution and blur. However, despite their wide adoption, heatmap regression approaches suffer from discretization-induced errors related to both the heatmap encoding and decoding process. In this work we show that these errors have a surprisingly large negative impact on facial alignment accuracy. To alleviate this problem, we propose a new approach for the heatmap encoding and decoding process by leveraging the underlying continuous distribution. To take full advantage of the newly proposed encoding-decoding mechanism, we also introduce a Siamese-based training that enforces heatmap consistency across various geometric image transformations. Our approach offers noticeable gains across multiple datasets setting a new state-of-the-art result in facial landmark localization. Code alongside the pretrained models will be made available at https://www.adrianbulat.com/face-alignment","url_abs":"https://arxiv.org/abs/2111.02360v1","url_pdf":"https://arxiv.org/pdf/2111.02360v1.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":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"heatmap","method_name":"Heatmap"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"SHR-FAN","rank_in_archive_order":8,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"4.13","NME_inter-ocular (%, Common)":"2.61","NME_inter-ocular (%, Full)":"2.94"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-300w-split-2-300w-lp","task":"Face Alignment","dataset":"300W Split 2 (300W-LP)","model":"SH-FAN","rank_in_archive_order":1,"of":4,"metrics":{"AUC@7 (bbox)":"71.1","NME (bbox)":"2.04","NME (inter-ocular)":"2.94"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-aflw-19","task":"Face Alignment","dataset":"AFLW-19","model":"SHR-FAN","rank_in_archive_order":5,"of":23,"metrics":{"AUC_box@0.07 (%, Full)":"70.0","NME_box (%, Full)":"2.14","NME_diag (%, Frontal)":"1.12","NME_diag (%, Full)":"1.31"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-cofw","task":"Face Alignment","dataset":"COFW","model":"SH-FAN","rank_in_archive_order":2,"of":28,"metrics":{"NME (inter-ocular)":"3.02%"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-cofw-68-300wlp","task":"Face Alignment","dataset":"COFW-68 (300WLP)","model":"SH-FAN","rank_in_archive_order":1,"of":4,"metrics":{"AUC@7":"64.9","NME (box)":"2.47"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-wflw","task":"Face Alignment","dataset":"WFLW","model":"SH-FAN","rank_in_archive_order":1,"of":36,"metrics":{"AUC@10 (inter-ocular)":"63.81","FR@10 (inter-ocular)":"1.55","NME (inter-ocular)":"3.72"},"uses_additional_data":false},{"leaderboard":"/sota/face-alignment-on-wfw-extra-data","task":"Face Alignment","dataset":"WFW (Extra Data)","model":"SH-FAN","rank_in_archive_order":1,"of":11,"metrics":{"AUC@10 (inter-ocular)":"63.1","FR@10 (inter-ocular)":"1.55","NME (inter-ocular)":"3.72"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.02360","atlas_url":"https://app.syntology.ai/?focus=2111.02360","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":"2111.02360"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.02360\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.02360"},"call":"get_concepts_for_paper(arxiv_id=\"2111.02360\")"}],"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":"d53301a3c4f527c1898d37d5f264d4bae44da71e498cdb78b683bc29efa7ecfc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}