Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

COCO dataset and benchmarks – Page 25 · SOTA2 Research

Research Datasets

COCO

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Text-to-Image Generation

COCO 2014-10K (val)

19.17FID

9

Image Quality Evaluation

COCO

24.02FID

9

Object Detection

MS COCO

21.07Ins. Error

9

Membership Inference Attack

COCO

0.797MPNet Score (Member)

9

Object Pointing

COCO

83.9F1@Point

9

Image captioning

COCO-Caption

68.41Macro F1

9

Semantic Differentiation

COCO Caption

7.68Wasserstein Distance

9

COCO subset (test)

47S2 Score

9

Training Data Attribution

COCO (train)

0.1Amortized Time (min)

9

Brightness-clustered generation

COCO 600 prompts (held-out)

0.07Gap

9

MS COCO Karpathy's split (val)

23.8Deletion @1

9

COCO (LQ-1)

63.37mIoU

9

COCO LQ-2

61.65IoU

9

COCO LQ-3

57.24IoU

9

Image Classification

COCO (val)

43.92Top-1 Accuracy

9

Object Detection

COCO-O painting

41.4mAP@.5:.95

9

Object Detection

COCO ID

49.9mAP.5.95

9

Text-to-Image Generation

COCO 10K prompts 2014 (karpathy 30K)

30.37HPS

9

COCO

58.3AP

9

Membership Inference Attack

MS-COCO (test)

96.86AUC

9

Semantic Segmentation

COCO-Object with background (val)

75.9pAcc

9

Image Captioning

COCO 2017

42.2BLEU-4

9

Backdoor Defense

COCO long prompts VD attack

0ASR (CLIP)

9

Image quality preservation on benign prompts

COCO

22.55FID

9

Spatial Reasoning

COCO 1&2obj

72.4Accuracy

9

Page 25 of 57

Popular tasks

Object Detection Image Captioning Instance Segmentation Semantic segmentation Text-to-Image Generation

Follow for updates

Join SOTA2 Contact