{"url":"/dataset/bioscan-5m","name":"BIOSCAN-5M","full_name":null,"description_markdown":"As part of an ongoing worldwide effort to comprehend and monitor insect biodiversity, we present the BIOSCAN-5M Insect dataset to the machine learning community. BIOSCAN-5M is a comprehensive dataset containing multi-modal information for over 5 million insect specimens, and it significantly expands existing image-based biological datasets by including taxonomic labels, raw nucleotide barcode sequences, assigned barcode index numbers, geographical information, and specimen size.\r\n\r\nEvery record has both image and DNA data. Each record of the BIOSCAN-5M dataset contains six primary attributes:\r\n\r\n    RGB image\r\n    DNA barcode sequence\r\n    Barcode Index Number (BIN)\r\n    Biological taxonomic classification\r\n    Geographical information\r\n    Specimen size","description_withheld":null,"homepage":"https://biodiversitygenomics.net/5M-insects/","introduced_date":"2024-06-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/bioscan-5m-a-multimodal-dataset-for-insect","title":"BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity","first_author":"Zahra Gharaee","url":null},"license":{"name":"Creative Commons Attribution 3.0 Unported","url":"https://creativecommons.org/licenses/by/3.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Biology","url":"/datasets/modality/biology"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Semi-Supervised Image Classification","url":"/task/semi-supervised-image-classification","datasets_with_task":"/datasets/task/semi-supervised-image-classification"},{"name":"Domain Generalization","url":"/task/domain-generalization","datasets_with_task":"/datasets/task/domain-generalization"},{"name":"Transfer Learning","url":"/task/transfer-learning","datasets_with_task":"/datasets/task/transfer-learning"},{"name":"Hierarchical Multi-label Classification","url":"/task/hierarchical-multi-label-classification","datasets_with_task":"/datasets/task/hierarchical-multi-label-classification"},{"name":"Multimodal Deep Learning","url":"/task/multimodal-deep-learning","datasets_with_task":"/datasets/task/multimodal-deep-learning"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Contrastive Learning","url":"/task/contrastive-learning","datasets_with_task":"/datasets/task/contrastive-learning"},{"name":"Self-Supervised Image Classification","url":"/task/self-supervised-image-classification","datasets_with_task":"/datasets/task/self-supervised-image-classification"},{"name":"Open-World Semi-Supervised Learning","url":"/task/open-world-semi-supervised-learning","datasets_with_task":"/datasets/task/open-world-semi-supervised-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BIOSCAN-5M"],"data_loaders":[{"repo":"https://github.com/zahrag/BIOSCAN-5M","url":"https://github.com/zahrag/BIOSCAN-5M","frameworks":["pytorch"]},{"repo":"https://github.com/bioscan-ml/dataset","url":"https://bioscan-dataset.readthedocs.io/","frameworks":["pytorch","jax"]}],"num_papers_in_archive":4,"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."}