{"url":"/dataset/dota","name":"DOTA","full_name":"Dataset for Object deTection in Aerial Images","description_markdown":"DOTA is a large-scale dataset for object detection in aerial images. It can be used to develop and evaluate object detectors in aerial images. The images are collected from different sensors and platforms. Each image is of the size in the range from 800 × 800 to 20,000 × 20,000 pixels and contains objects exhibiting a wide variety of scales, orientations, and shapes. The instances in DOTA images are annotated by experts in aerial image interpretation by arbitrary (8 d.o.f.) quadrilateral. We will continue to update DOTA, to grow in size and scope to reflect evolving real-world conditions. Now it has three versions:\r\n\r\nDOTA-v1.0 contains 15 common categories, 2,806 images and 188, 282 instances. The proportions of the training set, validation set, and testing set in DOTA-v1.0 are 1/2, 1/6, and 1/3, respectively.\r\n\r\nDOTA-v1.5 uses the same images as DOTA-v1.0, but the extremely small instances (less than 10 pixels) are also annotated. Moreover, a new category, ”container crane” is added. It contains 403,318 instances in total. The number of images and dataset splits are the same as DOTA-v1.0. This version was released for the DOAI Challenge 2019 on Object Detection in Aerial Images in conjunction with IEEE CVPR 2019.\r\n\r\nDOTA-v2.0 collects more Google Earth, GF-2 Satellite, and aerial images. There are 18 common categories, 11,268 images and 1,793,658 instances in DOTA-v2.0. Compared to DOTA-v1.5, it further adds the new categories of ”airport” and ”helipad”. The 11,268 images of DOTA are split into training, validation, test-dev, and test-challenge sets. To avoid the problem of overfitting, the proportion of training and validation set is smaller than the test set. Furthermore, we have two test sets, namely test-dev and test-challenge. Training contains 1,830 images and 268,627 instances. Validation contains 593 images and 81,048 instances. We released the images and ground truths for training and validation sets. Test-dev contains 2,792 images and 353,346 instances. We released the images but not the ground truths. Test-challenge contains 6,053 images and 1,090,637 instances.\r\n\r\nSource: [https://captain-whu.github.io/DOTA/index.html](https://captain-whu.github.io/DOTA/index.html)\r\nImage Source: [https://captain-whu.github.io/DOTA/](https://captain-whu.github.io/DOTA/)","description_withheld":null,"homepage":"https://captain-whu.github.io/DOTA/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/dota-a-large-scale-dataset-for-object","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","first_author":"Gui-Song Xia","url":null},"license":{"name":"Custom (non-commercial)","url":"https://captain-whu.github.io/DOTA/dataset.html"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"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"},{"name":"Oriented Object Detection","url":"/task/oriented-object-detection","datasets_with_task":"/datasets/task/oriented-object-detection"},{"name":"Dense Object Detection","url":"/task/dense-object-detection","datasets_with_task":"/datasets/task/dense-object-detection"}],"languages":[],"variants":["DOTA","DOTA 1.5","DOTA 1.0","DOTA 2.0"],"data_loaders":[],"num_papers_in_archive":293,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","task":"Object Detection In Aerial Images","dataset_variant":"DOTA","rows":58,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Strip R-CNN*","paper":"/paper/strip-r-cnn-large-strip-convolution-for","metrics":{"mAP":"82.75%"},"code_links":[{"title":"zcablii/Large-Selective-Kernel-Network","url":"https://github.com/zcablii/Large-Selective-Kernel-Network"},{"title":"yxb-nku/strip-r-cnn","url":"https://github.com/yxb-nku/strip-r-cnn"},{"title":"HVision-NKU/Strip-R-CNN","url":"https://github.com/HVision-NKU/Strip-R-CNN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1-0","task":"Object Detection In Aerial Images","dataset_variant":"DOTA 1.0","rows":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"RTMDet-R-l","paper":"/paper/rtmdet-an-empirical-study-of-designing-real","metrics":{"mAP":"81.33%"},"code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"open-mmlab/mmrotate","url":"https://github.com/open-mmlab/mmrotate"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"yxb-nku/strip-r-cnn","url":"https://github.com/yxb-nku/strip-r-cnn"},{"title":"HVision-NKU/Strip-R-CNN","url":"https://github.com/HVision-NKU/Strip-R-CNN"},{"title":"fiveai/MoCaE","url":"https://github.com/fiveai/MoCaE"},{"title":"yuyi1005/point2rbox-mmrotate","url":"https://github.com/yuyi1005/point2rbox-mmrotate"},{"title":"cszzshi/SimD","url":"https://github.com/cszzshi/SimD"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"V3Det/mmdetection-V3Det","url":"https://github.com/V3Det/mmdetection-V3Det"},{"title":"RangiLyu/mmdetection_test","url":"https://github.com/RangiLyu/mmdetection_test"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/legnet-lightweight-edge-gaussian-driven","title":"LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection","date":"2025-03-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/lwganet-a-lightweight-group-attention","title":"LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks","date":"2025-01-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/strip-r-cnn-large-strip-convolution-for","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","date":"2025-01-07","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/decouplenet-a-lightweight-backbone-network","title":"DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks","date":"2024-09-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/projecting-points-to-axes-oriented-object","title":"Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation","date":"2024-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/category-aware-dynamic-label-assignment-with","title":"Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposal","date":"2024-07-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mtp-advancing-remote-sensing-foundation-model","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","date":"2024-03-20","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","date":"2024-03-18","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/mocae-mixture-of-calibrated-experts","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","date":"2023-09-26","rows_on_this_dataset":1,"code_links":1,"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/spatial-transform-decoupling-for-oriented","title":"Spatial Transform Decoupling for Oriented Object Detection","date":"2023-08-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adaptive-rotated-convolution-for-rotated","title":"Adaptive Rotated Convolution for Rotated Object Detection","date":"2023-03-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rtmdet-an-empirical-study-of-designing-real","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","date":"2022-12-14","rows_on_this_dataset":2,"code_links":14,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":3,"samples_unverified":17,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","date":"2022-11-04","rows_on_this_dataset":4,"code_links":2,"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/few-could-be-better-than-all-feature-sampling","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","date":"2022-03-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/eautodet-efficient-architecture-search-for","title":"EAutoDet: Efficient Architecture Search for Object Detection","date":"2022-03-21","rows_on_this_dataset":1,"code_links":0,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/anchor-retouching-via-model-interaction-for","title":"Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images","date":"2021-12-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-general-gaussian-heatmap-labeling-for","title":"A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection","date":"2021-09-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/oriented-r-cnn-for-object-detection","title":"Oriented R-CNN for Object Detection","date":"2021-08-12","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/beyond-bounding-box-convex-hull-feature","title":"Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection","date":"2021-06-19","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-high-precision-bounding-box-for","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","date":"2021-06-03","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/oriented-reppoints-for-aerial-object","title":"Oriented RepPoints for Aerial Object Detection","date":"2021-05-24","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":0,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tricubenet-2d-kernel-based-object","title":"TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection","date":"2021-04-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/optimization-for-oriented-object-detection","title":"Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss","date":"2021-03-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/redet-a-rotation-equivariant-detector-for","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","date":"2021-03-13","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/rethinking-rotated-object-detection-with","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","date":"2021-01-28","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/cfc-net-a-critical-feature-capturing-network","title":"CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images","date":"2021-01-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dynamic-anchor-learning-for-arbitrary","title":"Dynamic Anchor Learning for Arbitrary-Oriented Object Detection","date":"2020-12-08","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/dense-label-encoding-for-boundary","title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","date":"2020-11-19","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/polardet-a-fast-more-precise-detector-for","title":"PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images","date":"2020-10-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/single-stage-rotation-decoupled-detector-for","title":"Single-Stage Rotation-Decoupled Detector for Oriented Object","date":"2020-10-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/align-deep-features-for-oriented-object","title":"Align Deep Features for Oriented Object Detection","date":"2020-08-21","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/oriented-object-detection-in-aerial-images","title":"Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors","date":"2020-08-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":3,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/piou-loss-towards-accurate-oriented-object","title":"PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments","date":"2020-07-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dynamic-refinement-network-for-oriented-and","title":"Dynamic Refinement Network for Oriented and Densely Packed Object Detection","date":"2020-05-20","rows_on_this_dataset":1,"code_links":1,"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/scrdet-detecting-small-cluttered-and-rotated","title":"SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing","date":"2020-04-28","rows_on_this_dataset":1,"code_links":5,"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/axis-learning-for-orientated-objects","title":"Axis Learning for Orientated Objects Detection in Aerial Images","date":"2020-03-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/arbitrary-oriented-object-detection-with","title":"On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited","date":"2020-03-12","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/oriented-objects-as-pairs-of-middle-lines","title":"Oriented Objects as pairs of Middle Lines","date":"2019-12-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gliding-vertex-on-the-horizontal-bounding-box","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","date":"2019-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-modulated-loss-for-rotated-object","title":"Learning Modulated Loss for Rotated Object Detection","date":"2019-11-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":0,"samples_unverified":13,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adaptive-period-embedding-for-representing","title":"Adaptive Period Embedding for Representing Oriented Objects in Aerial Images","date":"2019-06-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-roi-transformer-for-detecting","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","date":"2018-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/r2cnn-multi-dimensional-attention-based","title":"SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects","date":"2018-11-17","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/towards-multi-class-object-detection-in","title":"Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery","date":"2018-07-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dota-a-large-scale-dataset-for-object","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","date":"2017-11-28","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"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":16,"samples_harvested":86,"samples_ran":33,"samples_unverified":53,"pointer_only_for_licence":24,"papers_with_no_sample_that_ran":4,"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."}