{"url":"/dataset/bigearthnet","name":"BigEarthNet","full_name":null,"description_markdown":"BigEarthNet consists of 590,326 Sentinel-2 image patches, each of which is a section of i) 120x120 pixels for 10m bands; ii) 60x60 pixels for 20m bands; and iii) 20x20 pixels for 60m bands. \r\n\r\nSource: [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](/paper/bigearthnet-a-large-scale-benchmark-archive)","description_withheld":null,"homepage":"http://bigearth.net/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/bigearthnet-a-large-scale-benchmark-archive","title":"BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding","first_author":"Gencer Sumbul","url":null},"license":{"name":"Custom","url":"http://bigearth.net/downloads/documents/License.pdf"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Hyperspectral images","url":"/datasets/modality/hyperspectral-images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Multi-Label Image Classification","url":"/task/multi-label-image-classification","datasets_with_task":"/datasets/task/multi-label-image-classification"},{"name":"Scene Classification","url":"/task/scene-classification","datasets_with_task":"/datasets/task/scene-classification"}],"languages":[],"variants":["BigEarthNet","BigEarthNet (official test set)","BigEarthNet-S1 (official test set)"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/bigearthnet","frameworks":["tf","jax"]}],"num_papers_in_archive":85,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-image-classification-on","task":"Multi-Label Image Classification","dataset_variant":"BigEarthNet","rows":10,"metrics":["mAP (micro)","mAP (macro)","FScore","official split"],"first_row_in_archive_order":{"model":"MoCo-v2 (ResNet50, fine tune)","paper":"/paper/ssl4eo-s12-a-large-scale-multi-modal-multi","metrics":{"mAP (micro)":"91.8","official split":"No"},"code_links":[{"title":"zhu-xlab/ssl4eo-s12","url":"https://github.com/zhu-xlab/ssl4eo-s12"},{"title":"zhu-xlab/ssl4eo-review","url":"https://github.com/zhu-xlab/ssl4eo-review"},{"title":"zhu-xlab/dino-mm","url":"https://github.com/zhu-xlab/dino-mm"},{"title":"zhu-xlab/softcon","url":"https://github.com/zhu-xlab/softcon"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-image-classification-on-2","task":"Multi-Label Image Classification","dataset_variant":"BigEarthNet (official test set)","rows":6,"metrics":["mAP (micro)","F1 Score"],"first_row_in_archive_order":{"model":"FG-MAE (ViT-S/16)","paper":"/paper/feature-guided-masked-autoencoder-for-self","metrics":{"F1 Score":"80.8","mAP (micro)":"89.3"},"code_links":[{"title":"zhu-xlab/fgmae","url":"https://github.com/zhu-xlab/fgmae"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-image-classification-on-3","task":"Multi-Label Image Classification","dataset_variant":"BigEarthNet-S1 (official test set)","rows":3,"metrics":["mAP (micro)"],"first_row_in_archive_order":{"model":"FG-MAE (ViT-S/16)","paper":"/paper/feature-guided-masked-autoencoder-for-self","metrics":{"mAP (micro)":"82.7"},"code_links":[{"title":"zhu-xlab/fgmae","url":"https://github.com/zhu-xlab/fgmae"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/feature-guided-masked-autoencoder-for-self","title":"Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing","date":"2023-10-28","rows_on_this_dataset":6,"code_links":1,"syntology":null},{"paper":"/paper/dino-mc-self-supervised-contrastive-learning","title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","date":"2023-03-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ssl4eo-s12-a-large-scale-multi-modal-multi","title":"SSL4EO-S12: A Large-Scale Multi-Modal, Multi-Temporal Dataset for Self-Supervised Learning in Earth Observation","date":"2022-11-13","rows_on_this_dataset":5,"code_links":4,"syntology":null},{"paper":"/paper/self-supervised-learning-in-remote-sensing-a","title":"Self-supervised Learning in Remote Sensing: A Review","date":"2022-06-27","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficient-deep-learning-models-for-land-cover","title":"Benchmarking and scaling of deep learning models for land cover image classification","date":"2021-11-18","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/in-domain-representation-learning-for-remote-1","title":"In-domain representation learning for remote sensing","date":"2019-11-15","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":9,"samples_ran":1,"samples_unverified":8,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":2,"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."}