{"url":"/dataset/coco-o","name":"COCO-O","full_name":null,"description_markdown":"COCO-O(ut-of-distribution) contains 6 domains (sketch, cartoon, painting, weather, handmake, tattoo) of COCO objects which are hard to be detected by most existing detectors. The dataset has a total of 6,782 images and 26,624 labelled bounding boxes.","description_withheld":null,"homepage":"https://github.com/alibaba/easyrobust/tree/main/benchmarks/coco_o","introduced_date":"2023-07-25","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"2D Object Detection","url":"/task/2d-object-detection","datasets_with_task":"/datasets/task/2d-object-detection"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["COCO-O"],"data_loaders":[],"num_papers_in_archive":44,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-on-coco-o","task":"Object Detection","dataset_variant":"COCO-O","rows":45,"metrics":["Average mAP","Effective Robustness"],"first_row_in_archive_order":{"model":"EVA","paper":"/paper/eva-exploring-the-limits-of-masked-visual","metrics":{"Average mAP":"57.8","Effective Robustness":"28.86"},"code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"open-mmlab/mmselfsup","url":"https://github.com/open-mmlab/mmselfsup"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/beit"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/nms-strikes-back","title":"NMS Strikes Back","date":"2022-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grit-a-generative-region-to-text-transformer","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","date":"2022-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":5,"samples_unverified":3,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/eva-exploring-the-limits-of-masked-visual","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","date":"2022-11-14","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolov6-a-single-stage-object-detection","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","date":"2022-09-07","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolov7-trainable-bag-of-freebies-sets-new","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","date":"2022-07-06","rows_on_this_dataset":1,"code_links":21,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/coarse-to-fine-vision-language-pre-training","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","date":"2022-06-15","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vision-transformer-adapter-for-dense","title":"Vision Transformer Adapter for Dense Predictions","date":"2022-05-17","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/exploring-plain-vision-transformer-backbones","title":"Exploring Plain Vision Transformer Backbones for Object Detection","date":"2022-03-30","rows_on_this_dataset":2,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dino-detr-with-improved-denoising-anchor-1","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","date":"2022-03-07","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":7,"samples_unverified":8,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","rows_on_this_dataset":1,"code_links":54,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":80,"samples_ran":54,"samples_unverified":26,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/grounded-language-image-pre-training","title":"Grounded Language-Image Pre-training","date":"2021-12-07","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/yolox-exceeding-yolo-series-in-2021","title":"YOLOX: Exceeding YOLO Series in 2021","date":"2021-07-18","rows_on_this_dataset":2,"code_links":42,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":23,"samples_ran":1,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cbnetv2-a-composite-backbone-network","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","date":"2021-07-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pvtv2-improved-baselines-with-pyramid-vision","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","date":"2021-06-25","rows_on_this_dataset":1,"code_links":18,"syntology":null},{"paper":"/paper/dynamic-head-unifying-object-detection-heads","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","date":"2021-06-15","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":9,"samples_ran":7,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/you-only-look-at-one-sequence-rethinking","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","date":"2021-06-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":5,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/queryinst-parallelly-supervised-mask-query","title":"Instances as Queries","date":"2021-05-05","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/usb-universal-scale-object-detection","title":"USB: Universal-Scale Object Detection Benchmark","date":"2021-03-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/robust-and-accurate-object-detection-via","title":"Robust and Accurate Object Detection via Adversarial Learning","date":"2021-03-23","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/probabilistic-two-stage-detection","title":"Probabilistic two-stage detection","date":"2021-03-12","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/generalized-focal-loss-v2-learning-reliable","title":"Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection","date":"2020-11-25","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/deformable-detr-deformable-transformers-for-1","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","date":"2020-10-08","rows_on_this_dataset":1,"code_links":20,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":55,"samples_ran":29,"samples_unverified":26,"pointer_only_for_licence":21,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/varifocalnet-an-iou-aware-dense-object","title":"VarifocalNet: An IoU-aware Dense Object Detector","date":"2020-08-31","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/reppoints-v2-verification-meets-regression","title":"RepPoints V2: Verification Meets Regression for Object Detection","date":"2020-07-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/end-to-end-object-detection-with-transformers","title":"End-to-End Object Detection with Transformers","date":"2020-05-26","rows_on_this_dataset":1,"code_links":37,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":92,"samples_ran":59,"samples_unverified":33,"pointer_only_for_licence":19,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolov4-optimal-speed-and-accuracy-of-object","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","date":"2020-04-23","rows_on_this_dataset":1,"code_links":223,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":184,"samples_ran":24,"samples_unverified":160,"pointer_only_for_licence":8,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bridging-the-gap-between-anchor-based-and","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","date":"2019-12-05","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/efficientdet-scalable-and-efficient-object","title":"EfficientDet: Scalable and Efficient Object Detection","date":"2019-11-20","rows_on_this_dataset":1,"code_links":64,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":70,"samples_ran":11,"samples_unverified":59,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cascade-r-cnn-high-quality-object-detection","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","date":"2019-06-24","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/gcnet-non-local-networks-meet-squeeze","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","date":"2019-04-25","rows_on_this_dataset":1,"code_links":9,"syntology":null},{"paper":"/paper/fcos-fully-convolutional-one-stage-object","title":"FCOS: Fully Convolutional One-Stage Object Detection","date":"2019-04-02","rows_on_this_dataset":1,"code_links":87,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":40,"samples_ran":13,"samples_unverified":27,"pointer_only_for_licence":18,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hybrid-task-cascade-for-instance-segmentation","title":"Hybrid Task Cascade for Instance Segmentation","date":"2019-01-22","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","rows_on_this_dataset":1,"code_links":311,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":18,"samples_unverified":106,"pointer_only_for_licence":19,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/focal-loss-for-dense-object-detection","title":"Focal Loss for Dense Object Detection","date":"2017-08-07","rows_on_this_dataset":1,"code_links":234,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":11,"samples_unverified":0,"pointer_only_for_licence":6,"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":2,"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."}},{"paper":"/paper/ssd-single-shot-multibox-detector","title":"SSD: Single Shot MultiBox Detector","date":"2015-12-08","rows_on_this_dataset":1,"code_links":221,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":131,"samples_ran":19,"samples_unverified":112,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/faster-r-cnn-towards-real-time-object","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","date":"2015-06-04","rows_on_this_dataset":1,"code_links":196,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":59,"samples_unverified":65,"pointer_only_for_licence":42,"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":28,"samples_harvested":1168,"samples_ran":380,"samples_unverified":788,"pointer_only_for_licence":194,"papers_with_no_sample_that_ran":2,"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."}