{"url":"/dataset/yfcc-celeba","name":"YFCC-CelebA","full_name":null,"description_markdown":"The scales of the data accessible through internet search engines can reach hundreds of millions, or even billions. The existence of such large weak-labeled databases has gained importance in the training of face recognition algorithms. Starting with the publicly available YFCC100M, we propose a weakly-labeled subset for multi-label face recognition for self-supervised methods. A 392K image subset of YFCC100M of 128x128 images was obtained by querying for the 40 facial attributes. We made this dataset publicly available.","description_withheld":null,"homepage":"https://github.com/verimsu/YFCC392K-Face-Attributes-Dataset","introduced_date":"2023-09-05","introduced_date_note":null,"introduced_by":{"paper":"/paper/variational-self-supervised-contrastive","title":"Variational Self-Supervised Contrastive Learning Using Beta Divergence","first_author":"Mehmet Can Yavuz","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Face Recognition","url":"/task/face-recognition","datasets_with_task":"/datasets/task/face-recognition"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"}],"languages":[],"variants":["YFCC-CelebA"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"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."}