{"url":"/dataset/cplfw","name":"CPLFW","full_name":"Cross-Pose LFW","description_markdown":"A renovation of Labeled Faces in the Wild (LFW), the de facto standard testbed for unconstraint face verification. \r\n\r\nThere are three motivations behind the construction of CPLFW benchmark as follows:\r\n\r\n1.Establishing a relatively more difficult database to evaluate the performance of real world face verification so the effectiveness of several face verification methods can be fully justified.\r\n\r\n2.Continuing the intensive research on LFW with more realistic consideration on pose intra-class variation and fostering the research on cross-pose face verification in unconstrained situation. The challenge of CPLFW emphasizes pose difference to further enlarge intra-class variance. Also, negative pairs are deliberately selected to avoid different gender or race. CPLFW considers both the large intra-class variance and the tiny inter-class variance simultaneously.\r\n\r\n3.Maintaining the data size, the face verification protocol which provides a 'same/different' benchmark and the same identities in LFW, so one can easily apply CPLFW to evaluate the performance of face verification.\r\n\r\nSource: [CPLFW](http://whdeng.cn/CPLFW/index.html)","description_withheld":null,"homepage":"http://whdeng.cn/CPLFW/index.html","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Face Recognition","url":"/task/face-recognition","datasets_with_task":"/datasets/task/face-recognition"},{"name":"Face Verification","url":"/task/face-verification","datasets_with_task":"/datasets/task/face-verification"},{"name":"Lightweight Face Recognition","url":"/task/lightweight-face-recognition","datasets_with_task":"/datasets/task/lightweight-face-recognition"},{"name":"Synthetic Face Recognition","url":"/task/synthetic-face-recognition","datasets_with_task":"/datasets/task/synthetic-face-recognition"}],"languages":[],"variants":["CPLFW"],"data_loaders":[],"num_papers_in_archive":17,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/lightweight-face-recognition-on-cplfw","task":"Lightweight Face Recognition","dataset_variant":"CPLFW","rows":3,"metrics":["Accuracy","MFLOPs","MParams"],"first_row_in_archive_order":{"model":"EdgeFace - S (g=0.5)","paper":"/paper/edgeface-efficient-face-recognition-model-for","metrics":{"Accuracy":"0.9256","MFLOPs":"306.11","MParams":"3.65"},"code_links":[{"title":"otroshi/edgeface","url":"https://github.com/otroshi/edgeface"},{"title":"anjith2006/bob.paper.tbiom2023_edgeface","url":"https://github.com/anjith2006/bob.paper.tbiom2023_edgeface"},{"title":"bob/bob.paper.tbiom2023_edgeface","url":"https://gitlab.idiap.ch/bob/bob.paper.tbiom2023_edgeface"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/synthetic-face-recognition-on-cplfw","task":"Synthetic Face Recognition","dataset_variant":"CPLFW","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SynthDistill","paper":"/paper/synthdistill-face-recognition-with-knowledge","metrics":{"Accuracy":"0.8700"},"code_links":[{"title":"otroshi/synthdistill","url":"https://github.com/otroshi/synthdistill"},{"title":"bob/bob.paper.ijcb2023_synthdistill","url":"https://gitlab.idiap.ch/bob/bob.paper.ijcb2023_synthdistill"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-recognition-on-cplfw","task":"Face Recognition","dataset_variant":"CPLFW","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GhostFaceNetV2-1","paper":"/paper/ghostfacenets-lightweight-face-recognition","metrics":{"Accuracy":"0.9465"},"code_links":[{"title":"serengil/deepface","url":"https://github.com/serengil/deepface"},{"title":"Faceplugin-ltd/FaceRecognition-Android","url":"https://github.com/Faceplugin-ltd/FaceRecognition-Android"},{"title":"HamadYA/GhostFaceNets","url":"https://github.com/HamadYA/GhostFaceNets"},{"title":"FaceOnLive/Face-Recognition-SDK-Android","url":"https://github.com/FaceOnLive/Face-Recognition-SDK-Android"},{"title":"Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection","url":"https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection"},{"title":"Hazqeel09/ellzaf_ml","url":"https://github.com/Hazqeel09/ellzaf_ml"},{"title":"Armxyz1/Results-on-RFW","url":"https://github.com/Armxyz1/Results-on-RFW"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-verification-on-cplfw","task":"Face Verification","dataset_variant":"CPLFW","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DiscFace","paper":"/paper/discface-minimum-discrepancy-learning-for","metrics":{"Accuracy":"93.37"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/synthdistill-face-recognition-with-knowledge","title":"SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data","date":"2023-08-28","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/idiff-face-synthetic-based-face-recognition","title":"IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models","date":"2023-08-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":19,"samples_unverified":2,"pointer_only_for_licence":21,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/edgeface-efficient-face-recognition-model-for","title":"EdgeFace: Efficient Face Recognition Model for Edge Devices","date":"2023-07-04","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ghostfacenets-lightweight-face-recognition","title":"GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations","date":"2023-04-10","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/digiface-1m-1-million-digital-face-images-for","title":"DigiFace-1M: 1 Million Digital Face Images for Face Recognition","date":"2022-10-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/sface-sigmoid-constrained-hypersphere-loss-1","title":"SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition","date":"2022-05-24","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/elasticface-elastic-margin-loss-for-deep-face","title":"ElasticFace: Elastic Margin Loss for Deep Face Recognition","date":"2021-09-20","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pocketnet-extreme-lightweight-face","title":"PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation","date":"2021-08-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/discface-minimum-discrepancy-learning-for","title":"DiscFace: Minimum Discrepancy Learning for Deep Face Recognition","date":"2020-11-30","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":24,"samples_ran":22,"samples_unverified":2,"pointer_only_for_licence":24,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}