{"url":"/dataset/mineralimage5k","name":"MineralImage5k","full_name":"Benchmark for 5k raw mineral species recognition","description_markdown":"We present a  comprehensive dataset comprising a vast collection of raw mineral samples for the purpose of mineral recognition. The dataset encompasses more than 5,000 distinct mineral species and incorporates subsets for zero-shot and few-shot learning. In addition to the samples themselves, some entries in the dataset are accompanied by supplementary natural language descriptions, size measurements, and segmentation masks. For detailed information on each sample, please refer to the minerals_full.csv file.","description_withheld":null,"homepage":"","introduced_date":"2023-07-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/mineralimage5k-a-benchmark-for-zero-shot-raw","title":"MineralImage5k: A benchmark for zero-shot raw mineral visual recognition and description","first_author":"Sergey Nesteruk","url":null},"license":{"name":"MIT","url":"https://github.com/ai-forever/mineral-recognition/blob/main/LICENSE"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[{"name":"Few-Shot Image Classification","url":"/task/few-shot-image-classification","datasets_with_task":"/datasets/task/few-shot-image-classification"},{"name":"Image Segmentation","url":"/task/image-segmentation","datasets_with_task":"/datasets/task/image-segmentation"},{"name":"Zero-Shot Image Classification","url":"/task/zero-shot-image-classification","datasets_with_task":"/datasets/task/zero-shot-image-classification"},{"name":"regression","url":"/task/regression-1","datasets_with_task":"/datasets/task/regression-1"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["MineralImage5k"],"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."}