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

Fine-grained Recognition research benchmarks · SOTA2 Research

Fine-grained Recognition

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

iNaturalist 2018 (test)

84.7Top-1 Acc

20

Feb 26, 2026

BREEDS ENTITY-30 (test)

Fine upper-bound

94.02Accuracy

18

Feb 26, 2026

BREEDS ENTITY-13 (test)

Fine upper-bound

94.72Accuracy

18

Feb 26, 2026

BREEDS NONLIVING-26 (test)

Fine upper-bound

90.33Accuracy

18

Feb 26, 2026

BREEDS LIVING-17 (test)

90.97Accuracy

18

Feb 26, 2026

iWildCam-WILDS 1.0 (test-ID)

78.9Top-1 Acc

15

Feb 26, 2026

80.04Accuracy

8

Feb 27, 2026

Ten fine-grained recognition datasets (average)

0.18Memory (GB)

6

Jun 8, 2026

Ten fine-grained recognition datasets average

21.3DI2 Robustness Score

5

Jun 8, 2026

92Accuracy

4

Jun 16, 2026

97Accuracy

4

Jun 16, 2026

MLE-Bench iNaturalist 2019 FGVC6

24.45Score

2

May 27, 2026

MLE-Bench iMet 2020 FGVC7

68.04Score

2

May 27, 2026

Popular datasets

BREEDS Clear MLE-Bench iNaturalist iWildCam

Follow for updates

Join SOTA2 Contact