{"url":"/dataset/isaid","name":"iSAID","full_name":null,"description_markdown":"iSAID contains 655,451 object instances for 15 categories across 2,806 high-resolution images. The images of iSAID is the same as the DOTA-v1.0 dataset, which are manily collected from the Google Earth, some are taken by satellite JL-1, the others are taken by satellite GF-2 of the China Centre for Resources Satellite Data and Application.\r\n\r\nSource: [iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images](/paper/isaid-a-large-scale-dataset-for-instance)\r\nImage Source: [iSAID](https://captain-whu.github.io/iSAID/index.html)","description_withheld":null,"homepage":"https://captain-whu.github.io/iSAID/index.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/isaid-a-large-scale-dataset-for-instance","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","first_author":"Syed Waqas Zamir","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"Instance Segmentation","url":"/task/instance-segmentation","datasets_with_task":"/datasets/task/instance-segmentation"},{"name":"Open Vocabulary Semantic Segmentation","url":"/task/open-vocabulary-semantic-segmentation","datasets_with_task":"/datasets/task/open-vocabulary-semantic-segmentation"},{"name":"Object Detection In Aerial Images","url":"/task/object-detection-in-aerial-images","datasets_with_task":"/datasets/task/object-detection-in-aerial-images"},{"name":"Small Object Detection","url":"/task/small-object-detection","datasets_with_task":"/datasets/task/small-object-detection"}],"languages":[],"variants":["iSAID"],"data_loaders":[],"num_papers_in_archive":81,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-segmentation-on-isaid","task":"Semantic Segmentation","dataset_variant":"iSAID","rows":19,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SegNeXt-L","paper":"/paper/segnext-rethinking-convolutional-attention","metrics":{"mIoU":"70.3"},"code_links":[{"title":"open-mmlab/mmsegmentation","url":"https://github.com/open-mmlab/mmsegmentation"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"visual-attention-network/segnext","url":"https://github.com/visual-attention-network/segnext"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"Jittor/JSeg","url":"https://github.com/Jittor/JSeg"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/instance-segmentation-on-isaid","task":"Instance Segmentation","dataset_variant":"iSAID","rows":5,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PANet++","paper":"/paper/isaid-a-large-scale-dataset-for-instance","metrics":{"Average Precision":"40.00"},"code_links":[{"title":"CAPTAIN-WHU/iSAID_Devkit","url":"https://github.com/CAPTAIN-WHU/iSAID_Devkit"},{"title":"yeliudev/catnet","url":"https://github.com/yeliudev/catnet"},{"title":"Anirudh0707/Roads-and-Building-Segmentation","url":"https://github.com/Anirudh0707/Roads-and-Building-Segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-isaid","task":"Object Detection","dataset_variant":"iSAID","rows":5,"metrics":["Average Precision"],"first_row_in_archive_order":{"model":"PANet++","paper":"/paper/isaid-a-large-scale-dataset-for-instance","metrics":{"Average Precision":"47.0"},"code_links":[{"title":"CAPTAIN-WHU/iSAID_Devkit","url":"https://github.com/CAPTAIN-WHU/iSAID_Devkit"},{"title":"yeliudev/catnet","url":"https://github.com/yeliudev/catnet"},{"title":"Anirudh0707/Roads-and-Building-Segmentation","url":"https://github.com/Anirudh0707/Roads-and-Building-Segmentation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-15","task":"Open Vocabulary Semantic Segmentation","dataset_variant":"iSAID","rows":2,"metrics":["mIoU-"],"first_row_in_archive_order":{"model":"SkySense-O","paper":"/paper/skysense-a-multi-modal-remote-sensing","metrics":{"mIoU-":"43.9"},"code_links":[{"title":"jack-bo1220/awesome-remote-sensing-foundation-models","url":"https://github.com/jack-bo1220/awesome-remote-sensing-foundation-models"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/segearth-ov-towards-traning-free-open","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","date":"2024-10-02","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/skysense-a-multi-modal-remote-sensing","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","date":"2023-12-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/resolution-aware-design-of-atrous-rates-for","title":"Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks","date":"2023-07-26","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/farseg-foreground-aware-relation-network-for","title":"FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery","date":"2023-07-13","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/aerialformer-multi-resolution-transformer-for","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","date":"2023-06-12","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/segnext-rethinking-convolutional-attention","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","date":"2022-09-18","rows_on_this_dataset":4,"code_links":5,"syntology":null},{"paper":"/paper/advancing-plain-vision-transformer-towards","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","date":"2022-08-08","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/an-empirical-study-of-remote-sensing","title":"An Empirical Study of Remote Sensing Pretraining","date":"2022-04-06","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/factseg-foreground-activation-driven-small","title":"FactSeg: Foreground Activation Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery","date":"2021-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/foreground-aware-relation-network-for-1","title":"Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery","date":"2020-11-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/isaid-a-large-scale-dataset-for-instance","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","date":"2019-05-30","rows_on_this_dataset":4,"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/path-aggregation-network-for-instance","title":"Path Aggregation Network for Instance Segmentation","date":"2018-03-05","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","rows_on_this_dataset":4,"code_links":179,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":140,"samples_ran":42,"samples_unverified":98,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":158,"samples_ran":50,"samples_unverified":108,"pointer_only_for_licence":34,"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."}