{"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/improving-landmark-localization-with-semi","title":"Improving Landmark Localization with Semi-Supervised Learning","arxiv_id":"1709.01591","date":"2017-09-05","proceeding":"CVPR 2018 6","authors":["Sina Honari","Pavlo Molchanov","Stephen Tyree","Pascal Vincent","Christopher Pal","Jan Kautz"],"abstract":"We present two techniques to improve landmark localization in images from\npartially annotated datasets. Our primary goal is to leverage the common\nsituation where precise landmark locations are only provided for a small data\nsubset, but where class labels for classification or regression tasks related\nto the landmarks are more abundantly available. First, we propose the framework\nof sequential multitasking and explore it here through an architecture for\nlandmark localization where training with class labels acts as an auxiliary\nsignal to guide the landmark localization on unlabeled data. A key aspect of\nour approach is that errors can be backpropagated through a complete landmark\nlocalization model. Second, we propose and explore an unsupervised learning\ntechnique for landmark localization based on having a model predict equivariant\nlandmarks with respect to transformations applied to the image. We show that\nthese techniques, improve landmark prediction considerably and can learn\neffective detectors even when only a small fraction of the dataset has landmark\nlabels. We present results on two toy datasets and four real datasets, with\nhands and faces, and report new state-of-the-art on two datasets in the wild,\ne.g. with only 5\\% of labeled images we outperform previous state-of-the-art\ntrained on the AFLW dataset.","url_abs":"http://arxiv.org/abs/1709.01591v7","url_pdf":"http://arxiv.org/pdf/1709.01591v7.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":"small-data","task_name":"Small Data Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"RCN","rank_in_archive_order":41,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"7.78","NME_inter-ocular (%, Common)":"4.20","NME_inter-ocular (%, Full)":"4.90"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.01591","atlas_url":"https://app.syntology.ai/?focus=1709.01591","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":"1709.01591"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1709.01591\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1709.01591"},"call":"get_concepts_for_paper(arxiv_id=\"1709.01591\")"}],"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":"addf12708865b2da6904a661b2cd01de280caa83ba777882528a8f6ca5a14add","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}