Datasets › COCO-O

COCO-O

25 Jul 2023 archive 2025-07-28

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.

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Object Detection COCO-O EVA Average mAP 57.8 EVA: Exploring the Limits of Masked Visual... rwightman/pytorch-image-models +5 45 Compare

Papers archive 2025-07-28

30 shown of 39 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 44. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
NMS Strikes Back 1 1 12 Dec 2022 not harvested
GRiT: A Generative Region-to-text Transformer for Object Understanding 1 1 1 Dec 2022 ran 5 of 8 samples (3 unverified; 8 pointer-only for licence)
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale 6 1 14 Nov 2022 ran 1 of 3 samples (2 unverified)
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions 3 1 10 Nov 2022 ran 2 of 4 samples (2 unverified)
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications 7 1 7 Sep 2022 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors 21 1 6 Jul 2022 ran 1 of 11 samples (10 unverified)
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone 1 1 15 Jun 2022 ran 2 of 3 samples (1 unverified; 2 pointer-only for licence)
Vision Transformer Adapter for Dense Predictions 2 1 17 May 2022 not harvested
Exploring Plain Vision Transformer Backbones for Object Detection 11 2 30 Mar 2022 ran 1 of 4 samples (3 unverified)
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection 16 1 7 Mar 2022 ran 7 of 15 samples (8 unverified; 5 pointer-only for licence)
A ConvNet for the 2020s 54 1 10 Jan 2022 ran 54 of 80 samples (26 unverified; 11 pointer-only for licence)
Grounded Language-Image Pre-training 3 2 7 Dec 2021 ran 2 of 2 samples (0 unverified; 2 pointer-only for licence)
MViTv2: Improved Multiscale Vision Transformers for Classification and Detection 9 1 2 Dec 2021 not harvested
YOLOX: Exceeding YOLO Series in 2021 42 2 18 Jul 2021 ran 1 of 23 samples (22 unverified)
CBNet: A Composite Backbone Network Architecture for Object Detection 4 1 1 Jul 2021 ran 2 of 3 samples (1 unverified)
PVT v2: Improved Baselines with Pyramid Vision Transformer 18 1 25 Jun 2021 not harvested
Dynamic Head: Unifying Object Detection Heads with Attentions 3 2 15 Jun 2021 ran 7 of 9 samples (2 unverified)
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection 2 1 1 Jun 2021 ran 5 of 10 samples (5 unverified)
Instances as Queries 5 1 5 May 2021 ran 1 of 3 samples (2 unverified)
USB: Universal-Scale Object Detection Benchmark 1 2 25 Mar 2021 not harvested
Robust and Accurate Object Detection via Adversarial Learning 3 1 23 Mar 2021 not harvested
Probabilistic two-stage detection 3 1 12 Mar 2021 not harvested
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection 5 1 25 Nov 2020 not harvested
Deformable DETR: Deformable Transformers for End-to-End Object Detection 20 1 8 Oct 2020 ran 29 of 55 samples (26 unverified; 21 pointer-only for licence)
VarifocalNet: An IoU-aware Dense Object Detector 4 1 31 Aug 2020 ran 2 of 2 samples (0 unverified)
RepPoints V2: Verification Meets Regression for Object Detection 1 1 16 Jul 2020 not harvested
End-to-End Object Detection with Transformers 37 1 26 May 2020 ran 59 of 92 samples (33 unverified; 19 pointer-only for licence)
YOLOv4: Optimal Speed and Accuracy of Object Detection 223 1 23 Apr 2020 ran 24 of 184 samples (160 unverified; 8 pointer-only for licence)
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection 13 1 5 Dec 2019 ran 0 of 4 samples (4 unverified)
EfficientDet: Scalable and Efficient Object Detection 64 1 20 Nov 2019 ran 11 of 70 samples (59 unverified; 3 pointer-only for licence)

The full list of 39 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • COCO-O

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections