{"url":"/task/unsupervised-facial-landmark-detection","name":"Unsupervised Facial Landmark Detection","slug":"unsupervised-facial-landmark-detection","description_markdown":"Facial landmark detection in the unsupervised setting popularized by [1].  The evaluation occurs in two stages:\r\n(1) Embeddings are first learned in an unsupervised manner (i.e. without labels);\r\n(2) A simple regressor is trained to regress landmarks from the unsupervised embedding.\r\n\r\n[1]  Thewlis, James, Hakan Bilen, and Andrea Vedaldi. \"Unsupervised learning of object landmarks by factorized spatial embeddings.\" Proceedings of the IEEE International Conference on Computer Vision. 2017.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Unsupervised learning of object landmarks by factorized spatial embeddings](https://www.robots.ox.ac.uk/~vedaldi/assets/pubs/thewlis17unsupervised.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":15,"papers_with_code":13,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on-1","slug":"unsupervised-facial-landmark-detection-on-1","dataset":"MAFL","dataset_url":"/dataset/mafl","rows_in_archive":13,"metrics":["NME"],"first_row_in_archive_order":{"model":"Deep Latent Particles","paper_title":"Unsupervised Image Representation Learning with Deep Latent Particles","paper_url":"/paper/unsupervised-image-representation-learning","paper_date":"2022-05-31","arxiv_id":"2205.15821","code_links":[{"title":"taldatech/deep-latent-particles-pytorch","url":"https://github.com/taldatech/deep-latent-particles-pytorch"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on-5","slug":"unsupervised-facial-landmark-detection-on-5","dataset":"MAFL Unaligned","dataset_url":null,"rows_in_archive":9,"metrics":["NME"],"first_row_in_archive_order":{"model":"AutoLink","paper_title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","paper_url":"/paper/autolink-self-supervised-learning-of-human","paper_date":"2022-05-21","arxiv_id":"2205.10636","code_links":[{"title":"xingzhehe/AutoLink-Self-supervised-Learning-of-Human-Skeletons-and-Object-Outlines-by-Linking-Keypoints","url":"https://github.com/xingzhehe/AutoLink-Self-supervised-Learning-of-Human-Skeletons-and-Object-Outlines-by-Linking-Keypoints"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on","slug":"unsupervised-facial-landmark-detection-on","dataset":"300W","dataset_url":"/dataset/300w","rows_in_archive":4,"metrics":["NME"],"first_row_in_archive_order":{"model":"DVE","paper_title":"Unsupervised Learning of Landmarks by Descriptor Vector Exchange","paper_url":"/paper/unsupervised-learning-of-landmarks-by","paper_date":"2019-08-18","arxiv_id":"1908.06427","code_links":[{"title":"jamt9000/DVE","url":"https://github.com/jamt9000/DVE"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on-2","slug":"unsupervised-facial-landmark-detection-on-2","dataset":"AFLW (Zhang CVPR 2018 crops)","dataset_url":"/dataset/aflw","rows_in_archive":4,"metrics":["NME"],"first_row_in_archive_order":{"model":"Conditional Image Generation","paper_title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","paper_url":"/paper/unsupervised-learning-of-object-landmarks","paper_date":"2018-06-20","arxiv_id":"1806.07823","code_links":[{"title":"tomasjakab/imm","url":"https://github.com/tomasjakab/imm"},{"title":"hqng/imm-pytorch","url":"https://github.com/hqng/imm-pytorch"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on-7","slug":"unsupervised-facial-landmark-detection-on-7","dataset":"AFLW Unaligned","dataset_url":null,"rows_in_archive":4,"metrics":["NME"],"first_row_in_archive_order":{"model":"UPSDAP","paper_title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","paper_url":"/paper/unsupervised-part-segmentation-through","paper_date":"2021-05-26","arxiv_id":"2105.12405","code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-facial-landmark-detection-on-3","slug":"unsupervised-facial-landmark-detection-on-3","dataset":"AFLW-MTFL","dataset_url":"/dataset/aflw","rows_in_archive":3,"metrics":["NME"],"first_row_in_archive_order":{"model":"DVE","paper_title":"Unsupervised Learning of Landmarks by Descriptor Vector Exchange","paper_url":"/paper/unsupervised-learning-of-landmarks-by","paper_date":"2019-08-18","arxiv_id":"1908.06427","code_links":[{"title":"jamt9000/DVE","url":"https://github.com/jamt9000/DVE"}],"syntology":null}}],"datasets":[{"url":"/dataset/300w","name":"300W","full_name":"300 Faces-In-The-Wild","num_papers_in_archive":206},{"url":"/dataset/aflw","name":"AFLW","full_name":"Annotated Facial Landmarks in the Wild","num_papers_in_archive":154},{"url":"/dataset/mafl","name":"MAFL","full_name":"Multi-Attribute Facial Landmark","num_papers_in_archive":36}],"subtasks":[],"parent_tasks":[{"url":"/task/facial-landmark-detection","name":"Facial Landmark Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":13,"of":13,"tagged_in_all":15,"items":[{"url":"/paper/deep-feature-factorization-for-concept","title":"Deep Feature Factorization For Concept Discovery","date":"2018-06-26","arxiv_id":"1806.10206","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/unsupervised-part-based-disentangling-of","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","date":"2019-03-16","arxiv_id":"1903.06946","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-learning-of-a-facial","title":"Self-supervised learning of a facial attribute embedding from video","date":"2018-08-21","arxiv_id":"1808.06882","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-learning-of-object-landmarks","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","date":"2018-06-20","arxiv_id":"1806.07823","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/deforming-autoencoders-unsupervised","title":"Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance","date":"2018-06-18","arxiv_id":"1806.06503","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unsupervised-image-representation-learning","title":"Unsupervised Image Representation Learning with Deep Latent Particles","date":"2022-05-31","arxiv_id":"2205.15821","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/autolink-self-supervised-learning-of-human","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","date":"2022-05-21","arxiv_id":"2205.10636","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/ganseg-learning-to-segment-by-unsupervised","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","date":"2021-12-02","arxiv_id":"2112.01036","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/latentkeypointgan-controlling-gans-via-latent","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","date":"2021-03-29","arxiv_id":"2103.15812","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-landmarks-by","title":"Unsupervised Learning of Landmarks by Descriptor Vector Exchange","date":"2019-08-18","arxiv_id":"1908.06427","repositories_listed":1,"syntology":null},{"url":"/paper/scops-self-supervised-co-part-segmentation","title":"SCOPS: Self-Supervised Co-Part Segmentation","date":"2019-05-03","arxiv_id":"1905.01298","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-discovery-of-object-landmarks-as","title":"Unsupervised Discovery of Object Landmarks as Structural Representations","date":"2018-04-12","arxiv_id":"1804.04412","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/unsupervised-learning-of-object-landmarks-by","title":"Unsupervised learning of object landmarks by factorized spatial embeddings","date":"2017-05-05","arxiv_id":"1705.02193","repositories_listed":1,"syntology":null}],"syntology_records":7,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}