{"url":"/dataset/casia-webface","name":"CASIA-WebFace","full_name":null,"description_markdown":"The **CASIA-WebFace** dataset is used for face verification and face identification tasks. The dataset contains 494,414 face images of 10,575 real identities collected from the web.\r\n\r\nSource: [On Hallucinating Context and Background Pixels from a Face Mask using Multi-scale GANs](https://arxiv.org/abs/1811.07104)","description_withheld":null,"homepage":"","introduced_date":"2014-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-face-representation-from-scratch","title":"Learning Face Representation from Scratch","first_author":"Dong Yi","url":null},"license":{"name":"Custom (research-only, non-commercial)","url":"http://www.cbsr.ia.ac.cn/english/casia-webFace/casia-webfAce_AgreEmeNtS.pdf"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Super-Resolution","url":"/task/image-super-resolution","datasets_with_task":"/datasets/task/image-super-resolution"},{"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":"Metric Learning","url":"/task/metric-learning","datasets_with_task":"/datasets/task/metric-learning"},{"name":"Facial Inpainting","url":"/task/facial-inpainting","datasets_with_task":"/datasets/task/facial-inpainting"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Iranian Persian","url":"/datasets/language/iranian-persian"}],"variants":["WebFace","WebFace - 8x upscaling","CASIA-WebFace"],"data_loaders":[{"repo":"https://github.com/davidsandberg/facenet","url":"https://github.com/davidsandberg/facenet","frameworks":[]}],"num_papers_in_archive":415,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-super-resolution-on-webface-8x","task":"Image Super-Resolution","dataset_variant":"WebFace - 8x upscaling","rows":7,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"GFRNet","paper":"/paper/learning-warped-guidance-for-blind-face","metrics":{"PSNR":"27.21"},"code_links":[{"title":"csxmli2016/GFRNet","url":"https://github.com/csxmli2016/GFRNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-inpainting-on-webface","task":"Facial Inpainting","dataset_variant":"WebFace","rows":1,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"SymmFCNet (Full)","paper":"/paper/learning-symmetry-consistent-deep-cnns-for","metrics":{"PSNR":"27.22"},"code_links":[{"title":"csxmli2016/SymmFCNet","url":"https://github.com/csxmli2016/SymmFCNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/exemplar-guided-face-image-super-resolution","title":"Exemplar Guided Face Image Super-Resolution without Facial Landmarks","date":"2019-06-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-symmetry-consistent-deep-cnns-for","title":"Learning Symmetry Consistent Deep CNNs for Face Completion","date":"2018-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-warped-guidance-for-blind-face","title":"Learning Warped Guidance for Blind Face Restoration","date":"2018-04-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wavelet-srnet-a-wavelet-based-cnn-for-multi","title":"Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution","date":"2017-10-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hallucinating-very-low-resolution-unaligned","title":"Hallucinating Very Low-Resolution Unaligned and Noisy Face Images by Transformative Discriminative Autoencoders","date":"2017-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","rows_on_this_dataset":1,"code_links":140,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":72,"samples_ran":21,"samples_unverified":51,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/deep-cascaded-bi-network-for-face","title":"Deep Cascaded Bi-Network for Face Hallucination","date":"2016-07-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-image-super-resolution-using-very","title":"Accurate Image Super-Resolution Using Very Deep Convolutional Networks","date":"2015-11-14","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":1,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":2,"samples_harvested":78,"samples_ran":22,"samples_unverified":56,"pointer_only_for_licence":11,"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."}