{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/general-facial-representation-learning-in-a","title":"General Facial Representation Learning in a Visual-Linguistic Manner","arxiv_id":"2112.03109","date":"2021-12-06","proceeding":"CVPR 2022 1","authors":["Yinglin Zheng","Hao Yang","Ting Zhang","Jianmin Bao","Dongdong Chen","Yangyu Huang","Lu Yuan","Dong Chen","Ming Zeng","Fang Wen"],"abstract":"How to learn a universal facial representation that boosts all face analysis tasks? This paper takes one step toward this goal. In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner. On one hand, the framework involves a contrastive loss to learn high-level semantic meaning from image-text pairs. On the other hand, we propose exploring low-level information simultaneously to further enhance the face representation, by adding a masked image modeling. We perform pre-training on LAION-FACE, a dataset containing large amount of face image-text pairs, and evaluate the representation capability on multiple downstream tasks. We show that FaRL achieves better transfer performance compared with previous pre-trained models. We also verify its superiority in the low-data regime. More importantly, our model surpasses the state-of-the-art methods on face analysis tasks including face parsing and face alignment.","url_abs":"https://arxiv.org/abs/2112.03109v3","url_pdf":"https://arxiv.org/pdf/2112.03109v3.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":[{"paper_slug":"general-facial-representation-learning-in-a","repo_url":"https://github.com/FacePerceiver/FaRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"general-facial-representation-learning-in-a","repo_url":"https://github.com/willyfh/farl-face-segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"face-alignment","task_name":"Face Alignment"},{"task_slug":"face-parsing","task_name":"Face Parsing"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"FaRL-B (epoch 64)","rank_in_archive_order":3,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"4.42","NME_inter-ocular (%, Common)":"2.50","NME_inter-ocular (%, Full)":"2.88","NME_inter-pupil (%, Challenge)":"6.38","NME_inter-pupil (%, Common)":"3.46","NME_inter-pupil (%, Full)":"4.05"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-300w","task":"Face Alignment","dataset":"300W","model":"FaRL-B (epoch 16)","rank_in_archive_order":6,"of":48,"metrics":{"NME_inter-ocular (%, Challenge)":"4.45","NME_inter-ocular (%, Common)":"2.56","NME_inter-ocular (%, Full)":"2.93","NME_inter-pupil (%, Challenge)":"6.42","NME_inter-pupil (%, Common)":"3.53","NME_inter-pupil (%, Full)":"4.11"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-aflw-19","task":"Face Alignment","dataset":"AFLW-19","model":"FaRL-B (epoch 16)","rank_in_archive_order":2,"of":23,"metrics":{"AUC_box@0.07 (%, Full)":"81.3","NME_box (%, Full)":"1.334","NME_diag (%, Frontal)":"0.821","NME_diag (%, Full)":"0.943"},"uses_additional_data":true},{"leaderboard":"/sota/face-alignment-on-wfw-extra-data","task":"Face Alignment","dataset":"WFW (Extra Data)","model":"FaRL-B (epoch 16)","rank_in_archive_order":2,"of":11,"metrics":{"AUC@10 (inter-ocular)":"61.16","FR@10 (inter-ocular)":"1.76","NME (inter-ocular)":"3.96"},"uses_additional_data":true},{"leaderboard":"/sota/face-parsing-on-celebamask-hq","task":"Face Parsing","dataset":"CelebAMask-HQ","model":"FaRL-B","rank_in_archive_order":1,"of":7,"metrics":{"Mean F1":"89.56"},"uses_additional_data":true},{"leaderboard":"/sota/face-parsing-on-lapa","task":"Face Parsing","dataset":"LaPa","model":"FaRL-B","rank_in_archive_order":1,"of":11,"metrics":{"Mean F1":"93.88"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.03109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.03109"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FacePerceiver/FaRL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/willyfh/farl-face-segmentation","reach":null}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"53c56f01948d23d6","entry":"extract_face_mask","repo":"willyfh/farl-face-segmentation","repo_kind":"listed","path":"face_segmentation.py","file_url":"https://github.com/willyfh/farl-face-segmentation/blob/HEAD/face_segmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53c56f01948d23d6"}},{"code_sha256_prefix":"339ad1e042f08ab4","entry":"denormalize_points","repo":"FacePerceiver/FaRL","repo_kind":"official","path":"farl/network/geometry.py","file_url":"https://github.com/FacePerceiver/FaRL/blob/HEAD/farl/network/geometry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"339ad1e042f08ab4"}},{"code_sha256_prefix":"0e35c1ec061b3bba","entry":"load_checkpoint","repo":"FacePerceiver/FaRL","repo_kind":"official","path":"farl/network/common.py","file_url":"https://github.com/FacePerceiver/FaRL/blob/HEAD/farl/network/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"0e35c1ec061b3bba"}},{"code_sha256_prefix":"05bb69e5ecc10ba7","entry":"normalize_points","repo":"FacePerceiver/FaRL","repo_kind":"official","path":"farl/network/geometry.py","file_url":"https://github.com/FacePerceiver/FaRL/blob/HEAD/farl/network/geometry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"05bb69e5ecc10ba7"}},{"code_sha256_prefix":"dbd98ec960ae58b3","entry":"points2heatmap","repo":"FacePerceiver/FaRL","repo_kind":"official","path":"farl/network/geometry.py","file_url":"https://github.com/FacePerceiver/FaRL/blob/HEAD/farl/network/geometry.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"dbd98ec960ae58b3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}