{"url":"/dataset/disc21","name":"DISC21","full_name":"Dataset for ISC 2021","description_markdown":"**DISC21** is a benchmark for large-scale image similarity detection. This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021). The goal is to determine whether a query image is a modified copy of any image in a reference corpus of size 1~million. The benchmark features a variety of image transformations such as automated transformations, hand-crafted image edits and machine-learning based manipulations. This mimics real-life cases appearing in social media, for example for integrity-related problems dealing with misinformation and objectionable content. The strength of the image manipulations, and therefore the difficulty of the benchmark, is calibrated according to the performance of a set of baseline approaches. Both the query and reference set contain a majority of ``distractor'' images that do not match, which corresponds to a real-life needle-in-haystack setting, and the evaluation metric reflects that.","description_withheld":null,"homepage":"https://www.drivendata.org/competitions/79/","introduced_date":"2021-06-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-2021-image-similarity-dataset-and","title":"The 2021 Image Similarity Dataset and Challenge","first_author":"Matthijs Douze","url":null},"license":{"name":"Custom","url":"https://www.drivendata.org/competitions/79/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Similarity Detection","url":"/task/image-similarity-detection","datasets_with_task":"/datasets/task/image-similarity-detection"},{"name":"Image Similarity Search","url":"/task/image-similarity-search","datasets_with_task":"/datasets/task/image-similarity-search"}],"languages":[],"variants":["DISC21","DISC21 dev"],"data_loaders":[],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-similarity-detection-on-disc21-dev","task":"Image Similarity Detection","dataset_variant":"DISC21 dev","rows":4,"metrics":["w/o normalization","with normalization","Time (ms)","dimension","hardware"],"first_row_in_archive_order":{"model":"HOW+ASMK","paper":"/paper/the-2021-image-similarity-dataset-and","metrics":{"Time (ms)":"150","hardware":"Tesla P-100","w/o normalization":"17.32","with normalization":"37.15"},"code_links":[{"title":"facebookresearch/isc2021","url":"https://github.com/facebookresearch/isc2021"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/the-2021-image-similarity-dataset-and","title":"The 2021 Image Similarity Dataset and Challenge","date":"2021-06-17","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+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."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"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."}