{"url":"/dataset/bamboo","name":"Bamboo","full_name":null,"description_markdown":"Bamboo Dataset is a mega-scale and information-dense dataset for both classification and detection pre-training. It is built upon integrating **24** public datasets (e.g. **ImagenNet**, **Places365**, **Object365**, **OpenImages**) and added new annotations through **active learning**.  Bamboo has 69M image classification annotations and 32M object bounding boxes.","description_withheld":null,"homepage":"https://github.com/Davidzhangyuanhan/Bamboo","introduced_date":"2022-03-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/bamboo-building-mega-scale-vision-dataset","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","first_author":"Yuanhan Zhang","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"}],"languages":[],"variants":["Bamboo"],"data_loaders":[],"num_papers_in_archive":7,"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."}