{"url":"/sota/object-detection-on-coco-o","task":{"name":"Object Detection","url":"/task/object-detection","note":null},"dataset":{"name":"COCO-O","url":"/dataset/coco-o"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"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":["Average mAP","Effective Robustness"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average mAP":"higher","Effective Robustness":null}},"counts":{"rows":45,"rows_with_code":45,"rows_with_paper_page":45,"rows_dated":45,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"EVA","metrics":{"Average mAP":"57.8","Effective Robustness":"28.86"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/eva-exploring-the-limits-of-masked-visual","paper_url":"https://arxiv.org/abs/2211.07636v2","paper_title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":6,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"DETA\n(Swin-L)","metrics":{"Average mAP":"48.5","Effective Robustness":"20.15"},"uses_additional_data":false,"paper_date":"2022-12-12","paper":"/paper/nms-strikes-back","paper_url":"https://arxiv.org/abs/2212.06137v1","paper_title":"NMS Strikes Back","code":"https://github.com/jozhang97/deta","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"GLIP-L\n(Swin-L)","metrics":{"Average mAP":"48.0","Effective Robustness":"24.89"},"uses_additional_data":false,"paper_date":"2021-12-07","paper":"/paper/grounded-language-image-pre-training","paper_url":"https://arxiv.org/abs/2112.03857v2","paper_title":"Grounded Language-Image Pre-training","code":"https://github.com/microsoft/GLIP","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"GRiT\n(ViT-H)","metrics":{"Average mAP":"42.9","Effective Robustness":"15.72"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/grit-a-generative-region-to-text-transformer","paper_url":"https://arxiv.org/abs/2212.00280v1","paper_title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","code":"https://github.com/JialianW/GRiT","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8}},{"rank_in_archive_order":5,"model":"DINO (Swin-L)","metrics":{"Average mAP":"42.1","Effective Robustness":"15.76"},"uses_additional_data":false,"paper_date":"2022-03-07","paper":"/paper/dino-detr-with-improved-denoising-anchor-1","paper_url":"https://arxiv.org/abs/2203.03605v4","paper_title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","code":"https://github.com/IDEA-Research/Grounded-Segment-Anything","n_code_links":16,"syntology":{"n_ran":7,"n_unverified":8,"n_samples":15,"n_pointer_only_licence":5}},{"rank_in_archive_order":6,"model":"CBNetV2\n(Swin-L)","metrics":{"Average mAP":"39.0","Effective Robustness":"12.36"},"uses_additional_data":false,"paper_date":"2021-07-01","paper":"/paper/cbnetv2-a-composite-backbone-network","paper_url":"https://arxiv.org/abs/2107.00420v7","paper_title":"CBNet: A Composite Backbone Network Architecture for Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"ConvNeXt-XL\n(Cascade Mask R-CNN)","metrics":{"Average mAP":"37.5","Effective Robustness":"12.68"},"uses_additional_data":false,"paper_date":"2022-01-10","paper":"/paper/a-convnet-for-the-2020s","paper_url":"https://arxiv.org/abs/2201.03545v2","paper_title":"A ConvNet for the 2020s","code":"https://github.com/keras-team/keras/blob/master/keras/applications/convnext.py","n_code_links":54,"syntology":{"n_ran":54,"n_unverified":26,"n_samples":80,"n_pointer_only_licence":11}},{"rank_in_archive_order":8,"model":"InternImage-L (Cascade Mask R-CNN)","metrics":{"Average mAP":"37.0","Effective Robustness":"11.72"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/internimage-exploring-large-scale-vision","paper_url":"https://arxiv.org/abs/2211.05778v4","paper_title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","code":"https://github.com/opengvlab/internimage","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"DyHead\n(Swin-L)","metrics":{"Average mAP":"35.3","Effective Robustness":"10.00"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"ViTDet (ViT-H)","metrics":{"Average mAP":"34.3"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"ViT-Adapter (BEiTv2-L)","metrics":{"Average mAP":"34.25","Effective Robustness":"7.79"},"uses_additional_data":false,"paper_date":"2022-05-17","paper":"/paper/vision-transformer-adapter-for-dense","paper_url":"https://arxiv.org/abs/2205.08534v4","paper_title":"Vision Transformer Adapter for Dense Predictions","code":"https://github.com/czczup/vit-adapter","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"FIBER-B\n(Swin-B)","metrics":{"Average mAP":"33.7","Effective Robustness":"11.43"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/coarse-to-fine-vision-language-pre-training","paper_url":"https://arxiv.org/abs/2206.07643v2","paper_title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","code":"https://github.com/microsoft/fiber","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":13,"model":"QueryInst\n(Swin-L)","metrics":{"Average mAP":"33.2","Effective Robustness":"8.26"},"uses_additional_data":false,"paper_date":"2021-05-05","paper":"/paper/queryinst-parallelly-supervised-mask-query","paper_url":"https://arxiv.org/abs/2105.01928v3","paper_title":"Instances as Queries","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":2,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"YOLOv6-L6","metrics":{"Average mAP":"32.5","Effective Robustness":"6.73"},"uses_additional_data":false,"paper_date":"2022-09-07","paper":"/paper/yolov6-a-single-stage-object-detection","paper_url":"https://arxiv.org/abs/2209.02976v1","paper_title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":7,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":15,"model":"YOLOv7-E6E","metrics":{"Average mAP":"32.0","Effective Robustness":"6.42"},"uses_additional_data":false,"paper_date":"2022-07-06","paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","paper_url":"https://arxiv.org/abs/2207.02696v1","paper_title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","code":"https://github.com/pjreddie/darknet","n_code_links":21,"syntology":{"n_ran":1,"n_unverified":10,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"MViTV2-H\n(Cascade Mask R-CNN)","metrics":{"Average mAP":"30.9","Effective Robustness":"5.62"},"uses_additional_data":false,"paper_date":"2021-12-02","paper":"/paper/improved-multiscale-vision-transformers-for","paper_url":"https://arxiv.org/abs/2112.01526v2","paper_title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":9,"syntology":null},{"rank_in_archive_order":17,"model":"Det-AdvProp\n(EfficientNet-B5)","metrics":{"Average mAP":"30.8","Effective Robustness":"7.34"},"uses_additional_data":false,"paper_date":"2021-03-23","paper":"/paper/robust-and-accurate-object-detection-via","paper_url":"https://arxiv.org/abs/2103.13886v2","paper_title":"Robust and Accurate Object Detection via Adversarial Learning","code":"https://github.com/google/automl","n_code_links":3,"syntology":null},{"rank_in_archive_order":18,"model":"YOLOv4-P6","metrics":{"Average mAP":"30.4","Effective Robustness":"5.89"},"uses_additional_data":false,"paper_date":"2020-04-23","paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","paper_url":"https://arxiv.org/abs/2004.10934v1","paper_title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","code":"https://github.com/tensorflow/models/tree/master/official/vision/beta/projects/yolo","n_code_links":223,"syntology":{"n_ran":24,"n_unverified":160,"n_samples":184,"n_pointer_only_licence":8}},{"rank_in_archive_order":19,"model":"YOLOX-X","metrics":{"Average mAP":"30.3","Effective Robustness":"7.26"},"uses_additional_data":false,"paper_date":"2021-07-18","paper":"/paper/yolox-exceeding-yolo-series-in-2021","paper_url":"https://arxiv.org/abs/2107.08430v2","paper_title":"YOLOX: Exceeding YOLO Series in 2021","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":1,"n_unverified":22,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"CenterNet2\n(R2-101-DCN)","metrics":{"Average mAP":"29.5","Effective Robustness":"4.29"},"uses_additional_data":false,"paper_date":"2021-03-12","paper":"/paper/probabilistic-two-stage-detection","paper_url":"https://arxiv.org/abs/2103.07461v1","paper_title":"Probabilistic two-stage detection","code":"https://github.com/xingyizhou/CenterNet2","n_code_links":3,"syntology":null},{"rank_in_archive_order":21,"model":"GLIP-T\n(Swin-T)","metrics":{"Average mAP":"29.1","Effective Robustness":"8.11"},"uses_additional_data":false,"paper_date":"2021-12-07","paper":"/paper/grounded-language-image-pre-training","paper_url":"https://arxiv.org/abs/2112.03857v2","paper_title":"Grounded Language-Image Pre-training","code":"https://github.com/microsoft/GLIP","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":22,"model":"EfficientDet-D5\n(EfficientNet-B5)","metrics":{"Average mAP":"28.5","Effective Robustness":"5.44"},"uses_additional_data":false,"paper_date":"2019-11-20","paper":"/paper/efficientdet-scalable-and-efficient-object","paper_url":"https://arxiv.org/abs/1911.09070v7","paper_title":"EfficientDet: Scalable and Efficient Object Detection","code":"https://github.com/tensorflow/models/tree/master/research/object_detection","n_code_links":64,"syntology":{"n_ran":11,"n_unverified":59,"n_samples":70,"n_pointer_only_licence":3}},{"rank_in_archive_order":23,"model":"PVTv2-B5\n(Mask R-CNN)","metrics":{"Average mAP":"28.2","Effective Robustness":"6.85"},"uses_additional_data":false,"paper_date":"2021-06-25","paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","paper_url":"https://arxiv.org/abs/2106.13797v7","paper_title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","code":"https://github.com/rwightman/pytorch-image-models","n_code_links":18,"syntology":null},{"rank_in_archive_order":24,"model":"VFNet\n(RX-101-64x4d)","metrics":{"Average mAP":"28.0","Effective Robustness":"5.27"},"uses_additional_data":false,"paper_date":"2020-08-31","paper":"/paper/varifocalnet-an-iou-aware-dense-object","paper_url":"https://arxiv.org/abs/2008.13367v2","paper_title":"VarifocalNet: An IoU-aware Dense Object Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"GCNet\n(RX-101-32x4d-DCN)","metrics":{"Average mAP":"26.0","Effective Robustness":"4.38"},"uses_additional_data":false,"paper_date":"2019-04-25","paper":"/paper/gcnet-non-local-networks-meet-squeeze","paper_url":"http://arxiv.org/abs/1904.11492v1","paper_title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","code":"https://github.com/open-mmlab/mmdetection","n_code_links":9,"syntology":null},{"rank_in_archive_order":26,"model":"GFLv2\n(R2-101-DCN)","metrics":{"Average mAP":"25.1","Effective Robustness":"2.6"},"uses_additional_data":false,"paper_date":"2020-11-25","paper":"/paper/generalized-focal-loss-v2-learning-reliable","paper_url":"https://arxiv.org/abs/2011.12885v1","paper_title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":5,"syntology":null},{"rank_in_archive_order":27,"model":"RepPointsV2\n(RX-101-64x4d-DCN)","metrics":{"Average mAP":"24.9","Effective Robustness":"2.7"},"uses_additional_data":false,"paper_date":"2020-07-16","paper":"/paper/reppoints-v2-verification-meets-regression","paper_url":"https://arxiv.org/abs/2007.08508v1","paper_title":"RepPoints V2: Verification Meets Regression for Object Detection","code":"https://github.com/Scalsol/RepPointsV2","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"UniverseNet\n(R2-101-DCN)","metrics":{"Average mAP":"24.8"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/usb-universal-scale-object-detection","paper_url":"https://arxiv.org/abs/2103.14027v3","paper_title":"USB: Universal-Scale Object Detection Benchmark","code":"https://github.com/shinya7y/UniverseNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":29,"model":"YOLOX-S","metrics":{"Average mAP":"20.6","Effective Robustness":"2.48"},"uses_additional_data":false,"paper_date":"2021-07-18","paper":"/paper/yolox-exceeding-yolo-series-in-2021","paper_url":"https://arxiv.org/abs/2107.08430v2","paper_title":"YOLOX: Exceeding YOLO Series in 2021","code":"https://github.com/open-mmlab/mmdetection","n_code_links":42,"syntology":{"n_ran":1,"n_unverified":22,"n_samples":23,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"YOLOS-B\n(ViT-B)","metrics":{"Average mAP":"20.0","Effective Robustness":"1.05"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/you-only-look-at-one-sequence-rethinking","paper_url":"https://arxiv.org/abs/2106.00666v3","paper_title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","code":"https://github.com/huggingface/transformers","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":5,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"DyHead\n(ResNet-50)","metrics":{"Average mAP":"19.3","Effective Robustness":"0.16"},"uses_additional_data":false,"paper_date":"2021-06-15","paper":"/paper/dynamic-head-unifying-object-detection-heads","paper_url":"https://arxiv.org/abs/2106.08322v1","paper_title":"Dynamic Head: Unifying Object Detection Heads with Attentions","code":"https://github.com/open-mmlab/mmdetection","n_code_links":3,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"HTC\n(ResNet-50)","metrics":{"Average mAP":"19.1","Effective Robustness":"0.08"},"uses_additional_data":false,"paper_date":"2019-01-22","paper":"/paper/hybrid-task-cascade-for-instance-segmentation","paper_url":"http://arxiv.org/abs/1901.07518v2","paper_title":"Hybrid Task Cascade for Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":11,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"Deformable-DETR\n(ResNet-50)","metrics":{"Average mAP":"18.5","Effective Robustness":"-1.49"},"uses_additional_data":false,"paper_date":"2020-10-08","paper":"/paper/deformable-detr-deformable-transformers-for-1","paper_url":"https://arxiv.org/abs/2010.04159v4","paper_title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":20,"syntology":{"n_ran":29,"n_unverified":26,"n_samples":55,"n_pointer_only_licence":21}},{"rank_in_archive_order":34,"model":"Cascade R-CNN\n(ResNet-50)","metrics":{"Average mAP":"18.2","Effective Robustness":"0.02"},"uses_additional_data":false,"paper_date":"2019-06-24","paper":"/paper/cascade-r-cnn-high-quality-object-detection","paper_url":"https://arxiv.org/abs/1906.09756v1","paper_title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":4,"syntology":null},{"rank_in_archive_order":35,"model":"Mask R-CNN\n(ResNet-50)","metrics":{"Average mAP":"17.1"},"uses_additional_data":false,"paper_date":"2017-03-20","paper":"/paper/mask-r-cnn","paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","code":"https://github.com/tensorflow/models/tree/master/official/vision","n_code_links":179,"syntology":{"n_ran":42,"n_unverified":98,"n_samples":140,"n_pointer_only_licence":23}},{"rank_in_archive_order":36,"model":"DETR\n(ResNet-50)","metrics":{"Average mAP":"17.1","Effective Robustness":"-1.82"},"uses_additional_data":false,"paper_date":"2020-05-26","paper":"/paper/end-to-end-object-detection-with-transformers","paper_url":"https://arxiv.org/abs/2005.12872v3","paper_title":"End-to-End Object Detection with Transformers","code":"https://github.com/huggingface/transformers","n_code_links":37,"syntology":{"n_ran":59,"n_unverified":33,"n_samples":92,"n_pointer_only_licence":19}},{"rank_in_archive_order":37,"model":"ATSS\n(ResNet-50)","metrics":{"Average mAP":"16.8","Effective Robustness":"-0.91"},"uses_additional_data":false,"paper_date":"2019-12-05","paper":"/paper/bridging-the-gap-between-anchor-based-and","paper_url":"https://arxiv.org/abs/1912.02424v4","paper_title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":13,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"FCOS\n(ResNet-50)","metrics":{"Average mAP":"16.7","Effective Robustness":"0.25"},"uses_additional_data":false,"paper_date":"2019-04-02","paper":"/paper/fcos-fully-convolutional-one-stage-object","paper_url":"https://arxiv.org/abs/1904.01355v5","paper_title":"FCOS: Fully Convolutional One-Stage Object Detection","code":"https://github.com/open-mmlab/mmdetection","n_code_links":87,"syntology":{"n_ran":13,"n_unverified":27,"n_samples":40,"n_pointer_only_licence":18}},{"rank_in_archive_order":39,"model":"RetinaNet\n(ResNet-50)","metrics":{"Average mAP":"16.6","Effective Robustness":"0.18"},"uses_additional_data":false,"paper_date":"2017-08-07","paper":"/paper/focal-loss-for-dense-object-detection","paper_url":"http://arxiv.org/abs/1708.02002v2","paper_title":"Focal Loss for Dense Object Detection","code":"https://github.com/tensorflow/models","n_code_links":234,"syntology":{"n_ran":11,"n_unverified":0,"n_samples":11,"n_pointer_only_licence":6}},{"rank_in_archive_order":40,"model":"Faster R-CNN (ResNet-50-FPN)","metrics":{"Average mAP":"16.4","Effective Robustness":"-0.41"},"uses_additional_data":true,"paper_date":"2015-06-04","paper":"/paper/faster-r-cnn-towards-real-time-object","paper_url":"http://arxiv.org/abs/1506.01497v3","paper_title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","code":"https://github.com/facebookresearch/detectron2","n_code_links":196,"syntology":{"n_ran":59,"n_unverified":65,"n_samples":124,"n_pointer_only_licence":42}},{"rank_in_archive_order":41,"model":"YOLOv3\n(DarkNet-53)","metrics":{"Average mAP":"14.8","Effective Robustness":"-0.37"},"uses_additional_data":false,"paper_date":"2018-04-08","paper":"/paper/yolov3-an-incremental-improvement","paper_url":"http://arxiv.org/abs/1804.02767v1","paper_title":"YOLOv3: An Incremental Improvement","code":"https://github.com/open-mmlab/mmdetection","n_code_links":311,"syntology":{"n_ran":18,"n_unverified":106,"n_samples":124,"n_pointer_only_licence":19}},{"rank_in_archive_order":42,"model":"SSD (VGG-16)","metrics":{"Average mAP":"13.6","Effective Robustness":"0.36"},"uses_additional_data":false,"paper_date":"2015-12-08","paper":"/paper/ssd-single-shot-multibox-detector","paper_url":"http://arxiv.org/abs/1512.02325v5","paper_title":"SSD: Single Shot MultiBox Detector","code":"https://github.com/open-mmlab/mmdetection","n_code_links":221,"syntology":{"n_ran":19,"n_unverified":112,"n_samples":131,"n_pointer_only_licence":5}},{"rank_in_archive_order":43,"model":"ViTDet\n(ViT-H)","metrics":{"Effective Robustness":"7.89"},"uses_additional_data":false,"paper_date":"2022-03-30","paper":"/paper/exploring-plain-vision-transformer-backbones","paper_url":"https://arxiv.org/abs/2203.16527v2","paper_title":"Exploring Plain Vision Transformer Backbones for Object Detection","code":"https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet","n_code_links":11,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"UniverseNet (R2-101-DCN)","metrics":{"Effective Robustness":"1.86"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/usb-universal-scale-object-detection","paper_url":"https://arxiv.org/abs/2103.14027v3","paper_title":"USB: Universal-Scale Object Detection Benchmark","code":"https://github.com/shinya7y/UniverseNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"Mask R-CNN (ResNet-50)","metrics":{"Effective Robustness":"-0.11"},"uses_additional_data":false,"paper_date":"2017-03-20","paper":"/paper/mask-r-cnn","paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","code":"https://github.com/tensorflow/models/tree/master/official/vision","n_code_links":179,"syntology":{"n_ran":42,"n_unverified":98,"n_samples":140,"n_pointer_only_licence":23}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":33,"rows_with_any_sample_ran":31,"distinct_papers_with_graph_line":28,"distinct_papers_with_any_sample_ran":26,"samples_over_distinct_papers":{"n_ran":380,"n_unverified":788,"n_samples":1168,"n_pointer_only_licence":194,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":433,"n_unverified":913,"n_samples":1346,"n_pointer_only_licence":219,"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"}}}