{"url":"/sota/object-detection-in-aerial-images-on-dota-1","task":{"name":"Object Detection In Aerial Images","url":"/task/object-detection-in-aerial-images","note":null},"dataset":{"name":"DOTA","url":"/dataset/dota"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"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>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["mAP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"mAP":"higher"}},"counts":{"rows":58,"rows_with_code":50,"rows_with_paper_page":58,"rows_dated":58,"rows_using_additional_data":56},"rows":[{"rank_in_archive_order":1,"model":"Strip R-CNN*","metrics":{"mAP":"82.75%"},"uses_additional_data":true,"paper_date":"2025-01-07","paper":"/paper/strip-r-cnn-large-strip-convolution-for","paper_url":"https://arxiv.org/abs/2501.03775v3","paper_title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","code":"https://github.com/zcablii/Large-Selective-Kernel-Network","n_code_links":3,"syntology":null},{"rank_in_archive_order":2,"model":"MoCaE","metrics":{"mAP":"82.62%"},"uses_additional_data":true,"paper_date":"2023-09-26","paper":"/paper/mocae-mixture-of-calibrated-experts","paper_url":"https://arxiv.org/abs/2309.14976v4","paper_title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","code":"https://github.com/fiveai/MoCaE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":3,"model":"Strip R-CNN","metrics":{"mAP":"82.28%"},"uses_additional_data":true,"paper_date":"2025-01-07","paper":"/paper/strip-r-cnn-large-strip-convolution-for","paper_url":"https://arxiv.org/abs/2501.03775v3","paper_title":"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection","code":"https://github.com/zcablii/Large-Selective-Kernel-Network","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"Oriented-DETR","metrics":{"mAP":"82.26%"},"uses_additional_data":true,"paper_date":"2024-07-11","paper":"/paper/projecting-points-to-axes-oriented-object","paper_url":"https://arxiv.org/abs/2407.08489v1","paper_title":"Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation","code":"https://github.com/zhaozeyang108/Oriented-DETR","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"STD+HiViT-B","metrics":{"mAP":"82.24%"},"uses_additional_data":true,"paper_date":"2023-08-21","paper":"/paper/spatial-transform-decoupling-for-oriented","paper_url":"https://arxiv.org/abs/2308.10561v2","paper_title":"Spatial Transform Decoupling for Oriented Object Detection","code":"https://github.com/yuhongtian17/spatial-transform-decoupling","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CDLA-HOP","metrics":{"mAP":"82.02%"},"uses_additional_data":true,"paper_date":"2024-07-03","paper":"/paper/category-aware-dynamic-label-assignment-with","paper_url":"https://arxiv.org/abs/2407.03205v1","paper_title":"Category-Aware Dynamic Label Assignment with High-Quality Oriented Proposal","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"LSKNet-S*","metrics":{"mAP":"81.85%"},"uses_additional_data":true,"paper_date":"2024-03-18","paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","paper_url":"https://arxiv.org/abs/2403.11735v5","paper_title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","code":"https://github.com/zcablii/lsknet","n_code_links":2,"syntology":null},{"rank_in_archive_order":8,"model":"ARC","metrics":{"mAP":"81.77%"},"uses_additional_data":true,"paper_date":"2023-03-14","paper":"/paper/adaptive-rotated-convolution-for-rotated","paper_url":"https://arxiv.org/abs/2303.07820v2","paper_title":"Adaptive Rotated Convolution for Rotated Object Detection","code":"https://github.com/LeapLabTHU/ARC","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MAE+MTP(ViT-L+RVSA)","metrics":{"mAP":"81.66%"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_url":"https://arxiv.org/abs/2403.13430v2","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","code":"https://github.com/vitae-transformer/mtp","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"LSKNet-S","metrics":{"mAP":"81.64%"},"uses_additional_data":true,"paper_date":"2024-03-18","paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","paper_url":"https://arxiv.org/abs/2403.11735v5","paper_title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","code":"https://github.com/zcablii/lsknet","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"LSKNet-T","metrics":{"mAP":"81.37%"},"uses_additional_data":true,"paper_date":"2024-03-18","paper":"/paper/lsknet-a-foundation-lightweight-backbone-for","paper_url":"https://arxiv.org/abs/2403.11735v5","paper_title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","code":"https://github.com/zcablii/lsknet","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"ViTAE-B + RVSA-ORCN","metrics":{"mAP":"81.24%"},"uses_additional_data":true,"paper_date":"2022-08-08","paper":"/paper/advancing-plain-vision-transformer-towards","paper_url":"https://arxiv.org/abs/2208.03987v4","paper_title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"ViT-B + RVSA-ORCN","metrics":{"mAP":"81.01%"},"uses_additional_data":true,"paper_date":"2022-08-08","paper":"/paper/advancing-plain-vision-transformer-towards","paper_url":"https://arxiv.org/abs/2208.03987v4","paper_title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"Oriented RCNN","metrics":{"mAP":"80.87%"},"uses_additional_data":true,"paper_date":"2021-08-12","paper":"/paper/oriented-r-cnn-for-object-detection","paper_url":"https://arxiv.org/abs/2108.05699v1","paper_title":"Oriented R-CNN for Object Detection","code":"https://github.com/open-mmlab/mmrotate","n_code_links":5,"syntology":null},{"rank_in_archive_order":15,"model":"IMP+MTP(InternImage-XL)","metrics":{"mAP":"80.77%"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_url":"https://arxiv.org/abs/2403.13430v2","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","code":"https://github.com/vitae-transformer/mtp","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"PP-YOLOE-R-x","metrics":{"mAP":"80.73%"},"uses_additional_data":true,"paper_date":"2022-11-04","paper":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","paper_url":"https://arxiv.org/abs/2211.02386v1","paper_title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","code":"https://github.com/PaddlePaddle/Paddle","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"MAE+MTP(ViT-B+RVSA)","metrics":{"mAP":"80.67%"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/mtp-advancing-remote-sensing-foundation-model","paper_url":"https://arxiv.org/abs/2403.13430v2","paper_title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","code":"https://github.com/vitae-transformer/mtp","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"KLD+R3Det","metrics":{"mAP":"80.63%"},"uses_additional_data":true,"paper_date":"2021-06-03","paper":"/paper/learning-high-precision-bounding-box-for","paper_url":"https://arxiv.org/abs/2106.01883v5","paper_title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","code":"https://github.com/open-mmlab/mmrotate","n_code_links":2,"syntology":null},{"rank_in_archive_order":19,"model":"DEA-Net","metrics":{"mAP":"80.37%"},"uses_additional_data":true,"paper_date":"2021-12-13","paper":"/paper/anchor-retouching-via-model-interaction-for","paper_url":"https://arxiv.org/abs/2112.06701v1","paper_title":"Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images","code":"https://github.com/qxgeng/dea-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"GWD+R3Det","metrics":{"mAP":"80.23%"},"uses_additional_data":true,"paper_date":"2021-01-28","paper":"/paper/rethinking-rotated-object-detection-with","paper_url":"https://arxiv.org/abs/2101.11952v4","paper_title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","code":"https://github.com/open-mmlab/mmrotate","n_code_links":2,"syntology":null},{"rank_in_archive_order":21,"model":"ReDet","metrics":{"mAP":"80.10%"},"uses_additional_data":true,"paper_date":"2021-03-13","paper":"/paper/redet-a-rotation-equivariant-detector-for","paper_url":"https://arxiv.org/abs/2103.07733v1","paper_title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","code":"https://github.com/open-mmlab/mmrotate","n_code_links":4,"syntology":null},{"rank_in_archive_order":22,"model":"LEGNet-S","metrics":{"mAP":"80.03"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/legnet-lightweight-edge-gaussian-driven","paper_url":"https://arxiv.org/abs/2503.14012v1","paper_title":"LEGNet: Lightweight Edge-Gaussian Driven Network for Low-Quality Remote Sensing Image Object Detection","code":"https://github.com/lwcver/legnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"PP-YOLOE-R-l","metrics":{"mAP":"80.02%"},"uses_additional_data":true,"paper_date":"2022-11-04","paper":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","paper_url":"https://arxiv.org/abs/2211.02386v1","paper_title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","code":"https://github.com/PaddlePaddle/Paddle","n_code_links":2,"syntology":null},{"rank_in_archive_order":24,"model":"PP-YOLOE-R-m","metrics":{"mAP":"79.71%"},"uses_additional_data":true,"paper_date":"2022-11-04","paper":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","paper_url":"https://arxiv.org/abs/2211.02386v1","paper_title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","code":"https://github.com/PaddlePaddle/Paddle","n_code_links":2,"syntology":null},{"rank_in_archive_order":25,"model":"RBox","metrics":{"mAP":"79.59%"},"uses_additional_data":true,"paper_date":"2022-03-29","paper":"/paper/few-could-be-better-than-all-feature-sampling","paper_url":"https://arxiv.org/abs/2203.15221v2","paper_title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"S2A-Net","metrics":{"mAP":"79.42%"},"uses_additional_data":true,"paper_date":"2020-08-21","paper":"/paper/align-deep-features-for-oriented-object","paper_url":"https://arxiv.org/abs/2008.09397v3","paper_title":"Align Deep Features for Oriented Object Detection","code":"https://github.com/open-mmlab/mmrotate","n_code_links":3,"syntology":null},{"rank_in_archive_order":27,"model":"PP-YOLOE-R-s","metrics":{"mAP":"79.42%"},"uses_additional_data":true,"paper_date":"2022-11-04","paper":"/paper/pp-yoloe-r-an-efficient-anchor-free-rotated","paper_url":"https://arxiv.org/abs/2211.02386v1","paper_title":"PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector","code":"https://github.com/PaddlePaddle/Paddle","n_code_links":2,"syntology":null},{"rank_in_archive_order":28,"model":"LWGANet L2","metrics":{"mAP":"78.64"},"uses_additional_data":false,"paper_date":"2025-01-17","paper":"/paper/lwganet-a-lightweight-group-attention","paper_url":"https://arxiv.org/abs/2501.10040v1","paper_title":"LWGANet: A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks","code":"https://github.com/lwcver/lwganet","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"DecoupleNet D2","metrics":{"mAP":"78.04%"},"uses_additional_data":true,"paper_date":"2024-09-23","paper":"/paper/decouplenet-a-lightweight-backbone-network","paper_url":"https://ieeexplore.ieee.org/document/10685518","paper_title":"DecoupleNet: A Lightweight Backbone Network With Efficient Feature Decoupling for Remote Sensing Visual Tasks","code":"https://github.com/lwCVer/DecoupleNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"RDD","metrics":{"mAP":"77.75%"},"uses_additional_data":true,"paper_date":"2020-10-08","paper":"/paper/single-stage-rotation-decoupled-detector-for","paper_url":"https://www.mdpi.com/2072-4292/12/19/3262","paper_title":"Single-Stage Rotation-Decoupled Detector for Oriented Object","code":"https://github.com/Capino512/pytorch-rotation-decoupled-detector","n_code_links":1,"syntology":null},{"rank_in_archive_order":31,"model":"RSP-ViTAEv2-S-FPN-ORCN","metrics":{"mAP":"77.72%"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":32,"model":"Oriented RepPoints","metrics":{"mAP":"77.63%"},"uses_additional_data":true,"paper_date":"2021-05-24","paper":"/paper/oriented-reppoints-for-aerial-object","paper_url":"https://arxiv.org/abs/2105.11111v4","paper_title":"Oriented RepPoints for Aerial Object Detection","code":"https://github.com/LiWentomng/OrientedRepPoints","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"RIDet","metrics":{"mAP":"77.62%"},"uses_additional_data":true,"paper_date":"2021-03-22","paper":"/paper/optimization-for-oriented-object-detection","paper_url":"https://arxiv.org/abs/2103.11636v3","paper_title":"Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss","code":"https://github.com/ming71/RIDet","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"IMP-ViTAEv2-S-FPN-ORCN","metrics":{"mAP":"77.38%"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":35,"model":"DCL","metrics":{"mAP":"77.37%"},"uses_additional_data":true,"paper_date":"2020-11-19","paper":"/paper/dense-label-encoding-for-boundary","paper_url":"https://arxiv.org/abs/2011.09670v4","paper_title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","code":"https://github.com/yangxue0827/RotationDetection","n_code_links":3,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":36,"model":"EAutoDet","metrics":{"mAP":"77.05%"},"uses_additional_data":true,"paper_date":"2022-03-21","paper":"/paper/eautodet-efficient-architecture-search-for","paper_url":"https://arxiv.org/abs/2203.10747v1","paper_title":"EAutoDet: Efficient Architecture Search for Object Detection","code":null,"n_code_links":0,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":37,"model":"DLA+S2A-Net","metrics":{"mAP":"76.95%"},"uses_additional_data":true,"paper_date":"2020-12-08","paper":"/paper/dynamic-anchor-learning-for-arbitrary","paper_url":"https://arxiv.org/abs/2012.04150v2","paper_title":"Dynamic Anchor Learning for Arbitrary-Oriented Object Detection","code":"https://github.com/ming71/DAL","n_code_links":2,"syntology":null},{"rank_in_archive_order":38,"model":"GGHL","metrics":{"mAP":"76.95%"},"uses_additional_data":true,"paper_date":"2021-09-27","paper":"/paper/a-general-gaussian-heatmap-labeling-for","paper_url":"https://arxiv.org/abs/2109.12848v4","paper_title":"A General Gaussian Heatmap Label Assignment for Arbitrary-Oriented Object Detection","code":"https://github.com/Shank2358/GGHL","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"SCRDet++","metrics":{"mAP":"76.81%"},"uses_additional_data":true,"paper_date":"2020-04-28","paper":"/paper/scrdet-detecting-small-cluttered-and-rotated","paper_url":"https://arxiv.org/abs/2004.13316v2","paper_title":"SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing","code":"https://github.com/SJTU-Thinklab-Det/DOTA-DOAI","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":5,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"CFA","metrics":{"mAP":"76.67%"},"uses_additional_data":true,"paper_date":"2021-06-19","paper":"/paper/beyond-bounding-box-convex-hull-feature","paper_url":"http://openaccess.thecvf.com//content/CVPR2021/html/Guo_Beyond_Bounding-Box_Convex-Hull_Feature_Adaptation_for_Oriented_and_Densely_Packed_CVPR_2021_paper.html","paper_title":"Beyond Bounding-Box: Convex-Hull Feature Adaptation for Oriented and Densely Packed Object Detection","code":"https://github.com/open-mmlab/mmrotate","n_code_links":2,"syntology":null},{"rank_in_archive_order":41,"model":"PolarDet","metrics":{"mAP":"76.64%"},"uses_additional_data":true,"paper_date":"2020-10-17","paper":"/paper/polardet-a-fast-more-precise-detector-for","paper_url":"https://arxiv.org/abs/2010.08720v1","paper_title":"PolarDet: A Fast, More Precise Detector for Rotated Target in Aerial Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":42,"model":"RSP-ResNet-50-FPN-ORCN","metrics":{"mAP":"76.50%"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":43,"model":"CSL","metrics":{"mAP":"76.17%"},"uses_additional_data":true,"paper_date":"2020-03-12","paper":"/paper/arbitrary-oriented-object-detection-with","paper_url":"https://arxiv.org/abs/2003.05597v4","paper_title":"On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited","code":"https://github.com/hukaixuan19970627/yolov5_obb","n_code_links":4,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":44,"model":"RSP-Swin-T-FPN-ORCN","metrics":{"mAP":"76.12%"},"uses_additional_data":true,"paper_date":"2022-04-06","paper":"/paper/an-empirical-study-of-remote-sensing","paper_url":"https://arxiv.org/abs/2204.02825v4","paper_title":"An Empirical Study of Remote Sensing Pretraining","code":"https://github.com/vitae-transformer/vitae-transformer-remote-sensing","n_code_links":2,"syntology":null},{"rank_in_archive_order":45,"model":"APE","metrics":{"mAP":"75.75"},"uses_additional_data":true,"paper_date":"2019-06-22","paper":"/paper/adaptive-period-embedding-for-representing","paper_url":"https://arxiv.org/abs/1906.09447v1","paper_title":"Adaptive Period Embedding for Representing Oriented Objects in Aerial Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":46,"model":"BBAVectors","metrics":{"mAP":"75.36%"},"uses_additional_data":true,"paper_date":"2020-08-17","paper":"/paper/oriented-object-detection-in-aerial-images","paper_url":"https://arxiv.org/abs/2008.07043v2","paper_title":"Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors","code":"https://github.com/yijingru/BBAVectors-Oriented-Object-Detection","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"TricubeNet","metrics":{"mAP":"75.26%"},"uses_additional_data":true,"paper_date":"2021-04-23","paper":"/paper/tricubenet-2d-kernel-based-object","paper_url":"https://arxiv.org/abs/2104.11435v2","paper_title":"TricubeNet: 2D Kernel-Based Object Representation for Weakly-Occluded Oriented Object Detection","code":"https://github.com/qjadud1994/TricubeNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"Gliding Vertex","metrics":{"mAP":"75.02%"},"uses_additional_data":true,"paper_date":"2019-11-21","paper":"/paper/gliding-vertex-on-the-horizontal-bounding-box","paper_url":"https://arxiv.org/abs/1911.09358v2","paper_title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","code":"https://github.com/open-mmlab/mmrotate","n_code_links":1,"syntology":null},{"rank_in_archive_order":49,"model":"RSDet","metrics":{"mAP":"74.10%"},"uses_additional_data":true,"paper_date":"2019-11-19","paper":"/paper/learning-modulated-loss-for-rotated-object","paper_url":"https://arxiv.org/abs/1911.08299v3","paper_title":"Learning Modulated Loss for Rotated Object Detection","code":"https://github.com/Mrqianduoduo/RSDet-8P-4R","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":13,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":50,"model":"CFC-NET","metrics":{"mAP":"73.50%"},"uses_additional_data":true,"paper_date":"2021-01-18","paper":"/paper/cfc-net-a-critical-feature-capturing-network","paper_url":"https://arxiv.org/abs/2101.06849v2","paper_title":"CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images","code":"https://github.com/ming71/CFC-Net","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"DRN","metrics":{"mAP":"73.23%"},"uses_additional_data":true,"paper_date":"2020-05-20","paper":"/paper/dynamic-refinement-network-for-oriented-and","paper_url":"https://arxiv.org/abs/2005.09973v2","paper_title":"Dynamic Refinement Network for Oriented and Densely Packed Object Detection","code":"https://github.com/Anymake/DRN_CVPR2020","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":52,"model":"O2-DNet","metrics":{"mAP":"72.8%"},"uses_additional_data":true,"paper_date":"2019-12-23","paper":"/paper/oriented-objects-as-pairs-of-middle-lines","paper_url":"https://arxiv.org/abs/1912.10694v3","paper_title":"Oriented Objects as pairs of Middle Lines","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"SCRDet","metrics":{"mAP":"72.61%"},"uses_additional_data":true,"paper_date":"2018-11-17","paper":"/paper/r2cnn-multi-dimensional-attention-based","paper_url":"https://arxiv.org/abs/1811.07126v4","paper_title":"SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects","code":"https://github.com/DetectionTeamUCAS/RetinaNet_Tensorflow_Rotation","n_code_links":3,"syntology":null},{"rank_in_archive_order":54,"model":"RoI Transformer","metrics":{"mAP":"69.56%"},"uses_additional_data":true,"paper_date":"2018-12-01","paper":"/paper/learning-roi-transformer-for-detecting","paper_url":"http://arxiv.org/abs/1812.00155v1","paper_title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","code":"https://github.com/dingjiansw101/RoITransformer_DOTA","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":6,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":55,"model":"ICN","metrics":{"mAP":"68.16%"},"uses_additional_data":true,"paper_date":"2018-07-07","paper":"/paper/towards-multi-class-object-detection-in","paper_url":"http://arxiv.org/abs/1807.02700v3","paper_title":"Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":56,"model":"Axis Learning","metrics":{"mAP":"65.98%"},"uses_additional_data":true,"paper_date":"2020-03-20","paper":"/paper/axis-learning-for-orientated-objects","paper_url":"https://www.mdpi.com/2072-4292/12/6/908","paper_title":"Axis Learning for Orientated Objects Detection in Aerial Images","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"PIoU","metrics":{"mAP":"60.5%"},"uses_additional_data":true,"paper_date":"2020-07-19","paper":"/paper/piou-loss-towards-accurate-oriented-object","paper_url":"https://arxiv.org/abs/2007.09584v1","paper_title":"PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments","code":"https://github.com/clobotics/piou","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":58,"model":"FR-O (DOTA)","metrics":{"mAP":"52.93%"},"uses_additional_data":true,"paper_date":"2017-11-28","paper":"/paper/dota-a-large-scale-dataset-for-object","paper_url":"https://arxiv.org/abs/1711.10398v3","paper_title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":6,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":18,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":11,"samples_over_distinct_papers":{"n_ran":30,"n_unverified":36,"n_samples":66,"n_pointer_only_licence":24,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":41,"n_unverified":39,"n_samples":80,"n_pointer_only_licence":24,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}