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 10 · SOTA2 Research

Research Datasets

COCO

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Image-Text Retrieval

COCO 1.0 (test)

48.79R@1

24

COCO (subset 300 images, 30 categories)

98Accuracy

24

Object Detection

COCO

53.7mAP

24

Object Hallucination Mitigation

COCO 2014

56Cs Score

24

Text-to-Image Generation

COCO 512x512

17.84FID

24

Object Detection

COCO mini 10% (val)

33.6mAP

24

Image Reconstruction

COCO (test)

0.989CVU

24

Object Hallucination

COCO 512-token budget (test)

62.9Consistency Score

24

Object Hallucination

COCO 64-token budget (test)

0.328CS

24

Image Denoising

COCO 2017 (test)

6.021FID

24

Post-attack image integrity

COCO

30.15PSNR

24

Scene Text Recognition

COCO

80.4Accuracy

24

Semantic Segmentation

COCO 20^i

72.2mIoU

24

Object Detection

COCO-UniFS (val)

18.2AP

24

Semantic Segmentation

COCO-20i Fold-3

51.1mIoU

24

Semantic Segmentation

COCO-20i Fold-2

53.6mIoU

24

Semantic Segmentation

COCO 20i Fold-1

55.8mIoU

24

Semantic Segmentation

COCO-20i Fold-0

46.9mIoU

24

Image Captioning

COCO 2017 (val)

115.44CIDEr

24

Image Captioning

COCO c5 references online (test)

82.9BLEU-1

24

Semantic Segmentation

COCO-60 with background

43.3mIoU

23

Class Retrieval

COCO

63.7Acc@1

23

Image Watermarking

COCO Dataset

100ACC

23

Safe Text-to-Image Generation

COCO 3K

32.34FID

23

Image Captioning

COCO 17

107CIDEr

23

Page 10 of 57

Popular tasks

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

Follow for updates

Join SOTA2 Contact