{"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/look-across-elapse-disentangled","title":"Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition","arxiv_id":"1809.00338","date":"2018-09-02","proceeding":null,"authors":["Jian Zhao","Yu Cheng","Yi Cheng","Yang Yang","Haochong Lan","Fang Zhao","Lin Xiong","Yan Xu","Jianshu Li","Sugiri Pranata","ShengMei Shen","Junliang Xing","Hengzhu Liu","Shuicheng Yan","Jiashi Feng"],"abstract":"Despite the remarkable progress in face recognition related technologies,\nreliably recognizing faces across ages still remains a big challenge. The\nappearance of a human face changes substantially over time, resulting in\nsignificant intra-class variations. As opposed to current techniques for\nage-invariant face recognition, which either directly extract age-invariant\nfeatures for recognition, or first synthesize a face that matches target age\nbefore feature extraction, we argue that it is more desirable to perform both\ntasks jointly so that they can leverage each other. To this end, we propose a\ndeep Age-Invariant Model (AIM) for face recognition in the wild with three\ndistinct novelties. First, AIM presents a novel unified deep architecture\njointly performing cross-age face synthesis and recognition in a mutual\nboosting way. Second, AIM achieves continuous face rejuvenation/aging with\nremarkable photorealistic and identity-preserving properties, avoiding the\nrequirement of paired data and the true age of testing samples. Third, we\ndevelop effective and novel training strategies for end-to-end learning the\nwhole deep architecture, which generates powerful age-invariant face\nrepresentations explicitly disentangled from the age variation. Moreover, we\npropose a new large-scale Cross-Age Face Recognition (CAFR) benchmark dataset\nto facilitate existing efforts and push the frontiers of age-invariant face\nrecognition research. Extensive experiments on both our CAFR and several other\ncross-age datasets (MORPH, CACD and FG-NET) demonstrate the superiority of the\nproposed AIM model over the state-of-the-arts. Benchmarking our model on one of\nthe most popular unconstrained face recognition datasets IJB-C additionally\nverifies the promising generalizability of AIM in recognizing faces in the\nwild.","url_abs":"http://arxiv.org/abs/1809.00338v2","url_pdf":"http://arxiv.org/pdf/1809.00338v2.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":"look-across-elapse-disentangled","repo_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"age-invariant-face-recognition","task_name":"Age-Invariant Face Recognition"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"face-generation","task_name":"Face Generation"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"face-verification","task_name":"Face Verification"},{"task_slug":"morph","task_name":"MORPH"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-invariant-face-recognition-on-cacdvs","task":"Age-Invariant Face Recognition","dataset":"CACDVS","model":"AIM + CAFR","rank_in_archive_order":1,"of":9,"metrics":{"Accuracy":"99.76%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-cacdvs","task":"Age-Invariant Face Recognition","dataset":"CACDVS","model":"AIM","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"99.38%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-cafr","task":"Age-Invariant Face Recognition","dataset":"CAFR","model":"AIM","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"84.81%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-fg-net","task":"Age-Invariant Face Recognition","dataset":"FG-NET","model":"AIM","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"93.2%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-morph","task":"Age-Invariant Face Recognition","dataset":"MORPH Album2","model":"AIM + CAFR","rank_in_archive_order":1,"of":3,"metrics":{"Rank-1 Recognition Rate":"99.65%"},"uses_additional_data":false},{"leaderboard":"/sota/age-invariant-face-recognition-on-morph","task":"Age-Invariant Face Recognition","dataset":"MORPH Album2","model":"AIM","rank_in_archive_order":2,"of":3,"metrics":{"Rank-1 Recognition Rate":"99.13%"},"uses_additional_data":false},{"leaderboard":"/sota/face-verification-on-ijb-c","task":"Face Verification","dataset":"IJB-C","model":"AIM","rank_in_archive_order":24,"of":26,"metrics":{"TAR @ FAR=1e-2":"93.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.00338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.00338"}},"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/ZhaoJ9014/High_Performance_Face_Recognition","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"cd7d67a76db3a172","entry":"get4pts","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/MS-C1/align.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/MS-C1/align.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd7d67a76db3a172"}},{"code_sha256_prefix":"e475794319393649","entry":"get_upsampling_weight","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/ResNet/CASIA_WEB_FACE.PyTorch/models.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/ResNet/CASIA_WEB_FACE.PyTorch/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e475794319393649"}},{"code_sha256_prefix":"6fd1465a309afa5f","entry":"get_vgg_class_counts","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6fd1465a309afa5f"}},{"code_sha256_prefix":"c1f0ff9638b3e29f","entry":"make_weights_for_balanced_classes","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1f0ff9638b3e29f"}},{"code_sha256_prefix":"997ecf00348e78b9","entry":"rotate","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/MS-C1/align.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/MS-C1/align.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"997ecf00348e78b9"}},{"code_sha256_prefix":"2788c94fffe8ae7c","entry":"savgol_smooth","repo":"ZhaoJ9014/High_Performance_Face_Recognition","repo_kind":"official","path":"src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","file_url":"https://github.com/ZhaoJ9014/High_Performance_Face_Recognition/blob/HEAD/src/ResNet/CASIA_WEB_FACE.PyTorch/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2788c94fffe8ae7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}