{"url":"/task/object-detection-in-aerial-images","name":"Object Detection In Aerial Images","slug":"object-detection-in-aerial-images","description_markdown":"Object Detection in Aerial Images is the task of detecting objects from aerial images.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [DOTA: A Large-Scale Dataset for Object Detection in Aerial Images](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xia_DOTA_A_Large-Scale_CVPR_2018_paper.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":107,"papers_with_code":74,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":12,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1","slug":"object-detection-in-aerial-images-on-dota-1","dataset":"DOTA","dataset_url":"/dataset/dota","rows_in_archive":58,"metrics":["mAP"],"first_row_in_archive_order":{"model":"Strip R-CNN*","paper_title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","paper_url":"/paper/strip-r-cnn-large-strip-convolution-for","paper_date":"2025-01-07","arxiv_id":"2501.03775","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"}],"syntology":null}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dior-r","slug":"object-detection-in-aerial-images-on-dior-r","dataset":"DIOR-R","dataset_url":null,"rows_in_archive":9,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MAE+MTP(ViT-L+RVSA)","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","paper_url":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_date":"2024-03-20","arxiv_id":"2403.13430","code_links":[{"title":"vitae-transformer/mtp","url":"https://github.com/vitae-transformer/mtp"},{"title":"cuzyoung/crossearth","url":"https://github.com/cuzyoung/crossearth"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-hrsc2016","slug":"object-detection-in-aerial-images-on-hrsc2016","dataset":"HRSC2016","dataset_url":"/dataset/hrsc2016","rows_in_archive":9,"metrics":["mAP-07","mAP-12"],"first_row_in_archive_order":{"model":"CDLA-HOP","paper_title":"Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposal","paper_url":"/paper/category-aware-dynamic-label-assignment-with","paper_date":"2024-07-03","arxiv_id":"2407.03205","code_links":[],"syntology":null}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dior","slug":"object-detection-in-aerial-images-on-dior","dataset":"DIOR","dataset_url":"/dataset/dior","rows_in_archive":4,"metrics":["AP50"],"first_row_in_archive_order":{"model":"MAE+MTP(ViT-L+RVSA)","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","paper_url":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_date":"2024-03-20","arxiv_id":"2403.13430","code_links":[{"title":"vitae-transformer/mtp","url":"https://github.com/vitae-transformer/mtp"},{"title":"cuzyoung/crossearth","url":"https://github.com/cuzyoung/crossearth"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-fair1m-2","slug":"object-detection-in-aerial-images-on-fair1m-2","dataset":"FAIR1M-2.0","dataset_url":null,"rows_in_archive":3,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MAE+MTP(ViT-L+RVSA)","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","paper_url":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_date":"2024-03-20","arxiv_id":"2403.13430","code_links":[{"title":"vitae-transformer/mtp","url":"https://github.com/vitae-transformer/mtp"},{"title":"cuzyoung/crossearth","url":"https://github.com/cuzyoung/crossearth"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-xview","slug":"object-detection-in-aerial-images-on-xview","dataset":"xView","dataset_url":"/dataset/xview","rows_in_archive":3,"metrics":["AP50"],"first_row_in_archive_order":{"model":"MAE+MTP(ViT-L+RVSA)","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","paper_url":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_date":"2024-03-20","arxiv_id":"2403.13430","code_links":[{"title":"vitae-transformer/mtp","url":"https://github.com/vitae-transformer/mtp"},{"title":"cuzyoung/crossearth","url":"https://github.com/cuzyoung/crossearth"}],"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-dota-1-0","slug":"object-detection-in-aerial-images-on-dota-1-0","dataset":"DOTA 1.0","dataset_url":"/dataset/dota","rows_in_archive":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"RTMDet-R-l","paper_title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","paper_url":"/paper/rtmdet-an-empirical-study-of-designing-real","paper_date":"2022-12-14","arxiv_id":"2212.07784","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"}],"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}}},{"leaderboard":"/sota/object-detection-in-aerial-images-on-vme-cdsi","slug":"object-detection-in-aerial-images-on-vme-cdsi","dataset":"VME & CDSI","dataset_url":"/dataset/vme-cdsi","rows_in_archive":1,"metrics":["mAP50"],"first_row_in_archive_order":{"model":"DINO","paper_title":"VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond","paper_url":"/paper/vme-a-satellite-imagery-dataset-and-benchmark","paper_date":"2025-05-28","arxiv_id":"2505.22353","code_links":[{"title":"nalemadi/VME_CDSI_dataset_benchmark","url":"https://github.com/nalemadi/VME_CDSI_dataset_benchmark"}],"syntology":null}}],"datasets":[{"url":"/dataset/dota","name":"DOTA","full_name":"Dataset for Object deTection in Aerial Images","num_papers_in_archive":293},{"url":"/dataset/xview","name":"xView","full_name":"","num_papers_in_archive":93},{"url":"/dataset/isaid","name":"iSAID","full_name":"","num_papers_in_archive":81},{"url":"/dataset/aid","name":"AID","full_name":"Aerial Image Dataset","num_papers_in_archive":40},{"url":"/dataset/dior","name":"DIOR","full_name":"","num_papers_in_archive":17},{"url":"/dataset/hrsc2016","name":"HRSC2016","full_name":"High resolution ship collections 2016","num_papers_in_archive":12},{"url":"/dataset/landcover-ai","name":"LandCover.ai","full_name":"Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagery","num_papers_in_archive":11},{"url":"/dataset/dota-2-0","name":"DOTA 2.0","full_name":"Dataset of Object deTection in Aerial images","num_papers_in_archive":10},{"url":"/dataset/soda-a","name":"SODA-A","full_name":"","num_papers_in_archive":7},{"url":"/dataset/c2a-dataset-human-detection-in-disaster","name":"C2A: Human Detection in Disaster Scenarios","full_name":"Combination to Application","num_papers_in_archive":2},{"url":"/dataset/fmars","name":"FMARS","full_name":"Foundation Models Annotation in Remote Sensing","num_papers_in_archive":1},{"url":"/dataset/vme-cdsi","name":"VME & CDSI","full_name":"Vehicles in the Middle East (VME) & Car Detection in Satellite Imagery (CDSI) datasets","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/object-detection","name":"Object Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":74,"tagged_in_all":107,"items":[{"url":"/paper/rtmdet-an-empirical-study-of-designing-real","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","date":"2022-12-14","arxiv_id":"2212.07784","repositories_listed":14,"syntology":{"n":20,"n_ran":3,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/r3det-refined-single-stage-detector-with","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","date":"2019-08-15","arxiv_id":"1908.05612","repositories_listed":10,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/dota-a-large-scale-dataset-for-object","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","date":"2017-11-28","arxiv_id":"1711.10398","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/oriented-r-cnn-for-object-detection","title":"Oriented R-CNN for Object Detection","date":"2021-08-12","arxiv_id":"2108.05699","repositories_listed":5,"syntology":null},{"url":"/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","arxiv_id":"2004.13316","repositories_listed":5,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/redet-a-rotation-equivariant-detector-for","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","date":"2021-03-13","arxiv_id":"2103.07733","repositories_listed":4,"syntology":null},{"url":"/paper/arbitrary-oriented-object-detection-with","title":"On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited","date":"2020-03-12","arxiv_id":"2003.05597","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/strip-r-cnn-large-strip-convolution-for","title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","date":"2025-01-07","arxiv_id":"2501.03775","repositories_listed":3,"syntology":null},{"url":"/paper/the-kfiou-loss-for-rotated-object-detection-1","title":"The KFIoU Loss for Rotated Object Detection","date":"2022-01-29","arxiv_id":"2201.12558","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/dense-label-encoding-for-boundary","title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","date":"2020-11-19","arxiv_id":"2011.09670","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/align-deep-features-for-oriented-object","title":"Align Deep Features for Oriented Object Detection","date":"2020-08-21","arxiv_id":"2008.09397","repositories_listed":3,"syntology":null},{"url":"/paper/r2cnn-multi-dimensional-attention-based","title":"SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects","date":"2018-11-17","arxiv_id":"1811.07126","repositories_listed":3,"syntology":null},{"url":"/paper/mtp-advancing-remote-sensing-foundation-model","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","date":"2024-03-20","arxiv_id":"2403.13430","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/lsknet-a-foundation-lightweight-backbone-for","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","date":"2024-03-18","arxiv_id":"2403.11735","repositories_listed":2,"syntology":null},{"url":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","date":"2022-11-04","arxiv_id":"2211.02386","repositories_listed":2,"syntology":null},{"url":"/paper/advancing-plain-vision-transformer-towards","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","date":"2022-08-08","arxiv_id":"2208.03987","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/an-empirical-study-of-remote-sensing","title":"An Empirical Study of Remote Sensing Pretraining","date":"2022-04-06","arxiv_id":"2204.02825","repositories_listed":2,"syntology":null},{"url":"/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","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/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","arxiv_id":"2106.01883","repositories_listed":2,"syntology":null},{"url":"/paper/oriented-reppoints-for-aerial-object","title":"Oriented RepPoints for Aerial Object Detection","date":"2021-05-24","arxiv_id":"2105.11111","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/object-detection-in-aerial-images-a-large","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","date":"2021-02-24","arxiv_id":"2102.12219","repositories_listed":2,"syntology":null},{"url":"/paper/rethinking-rotated-object-detection-with","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","date":"2021-01-28","arxiv_id":"2101.11952","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-anchor-learning-for-arbitrary","title":"Dynamic Anchor Learning for Arbitrary-Oriented Object Detection","date":"2020-12-08","arxiv_id":"2012.04150","repositories_listed":2,"syntology":null},{"url":"/paper/learning-modulated-loss-for-rotated-object","title":"Learning Modulated Loss for Rotated Object Detection","date":"2019-11-19","arxiv_id":"1911.08299","repositories_listed":2,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/learning-roi-transformer-for-oriented-object","title":"Learning RoI Transformer for Oriented Object Detection in Aerial Images","date":"2019-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/dronet-efficient-convolutional-neural-network","title":"DroNet: Efficient convolutional neural network detector for real-time UAV applications","date":"2018-07-18","arxiv_id":"1807.06789","repositories_listed":2,"syntology":null},{"url":"/paper/xview-objects-in-context-in-overhead-imagery","title":"xView: Objects in Context in Overhead Imagery","date":"2018-02-22","arxiv_id":"1802.07856","repositories_listed":2,"syntology":null},{"url":"/paper/vme-a-satellite-imagery-dataset-and-benchmark","title":"VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond","date":"2025-05-28","arxiv_id":"2505.22353","repositories_listed":1,"syntology":null},{"url":"/paper/self-prompting-analogical-reasoning-for-uav","title":"self-prompting analogical reasoning for uav object detection","date":"2025-04-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","arxiv_id":"2503.14012","repositories_listed":1,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}