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

Image Classification research benchmarks – Page 281 · SOTA2 Research

Image Classification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MNIST i.i.d. partitioning (test)

A single SGD, no Pac-Man

97.49Accuracy (Complete)

4

Apr 16, 2026

60.6AUBC

4

Apr 15, 2026

76.2AUBC

4

Apr 15, 2026

52.5AUBC

4

Apr 15, 2026

84.7AUBC

4

Apr 15, 2026

81.3AUBC

4

Apr 15, 2026

0.863AUBC

4

Apr 15, 2026

Camelyon Hospital 5 17 (test)

16.08Error Rate

4

Apr 14, 2026

TVHL-DR Ophthalmology OCT

90.38Accuracy

4

Apr 13, 2026

TVHL-DME Ophthalmology OCT

98.21Accuracy

4

Apr 13, 2026

OCTID Ophthalmology OCT

97.13Accuracy

4

Apr 13, 2026

Retina Retinology Fundus

88.4Accuracy

4

Apr 13, 2026

PAPILA Retinology Fundus

88.3Accuracy

4

Apr 13, 2026

Glaucoma Retinology Fundus

90.97Accuracy

4

Apr 13, 2026

APTOS Retinology Fundus

93.43Accuracy

4

Apr 13, 2026

ImageNet Distribution-based label imbalance 10 tasks (100 classes per task) beta = 0.5

Fed-TaLoRA (block 1-6, w/ MLP)

74.8FAA

4

Apr 13, 2026

ImageNet Quantity-based label imbalance 10 tasks (100 classes per task) alpha=60

Fed-TaLoRA (block 1-6, w/ MLP)

73.5FAA

4

Apr 13, 2026

Kandinsky One-triangle

100Accuracy

4

Apr 10, 2026

Kandinsky One-red

100Accuracy

4

Apr 10, 2026

Kandinsky Two-pair

75Accuracy

4

Apr 10, 2026

Flowers, DTD, UCF, Food, GTSRB, EuroSAT, Pets, Cars, SUN, SVHN (test)

55Accuracy (Flowers)

4

Apr 3, 2026

Aircraft, Caltech101, DTD, Flowers, Food, Pets, SUN397

81.9Average Accuracy

4

Apr 2, 2026

90.4Worst-Group Accuracy

4

Apr 1, 2026

35Accuracy (Seen)

4

Mar 31, 2026

51.3Seen Score

4

Mar 31, 2026

Page 281 of 333

Popular datasets

CIFAR ImageNet MNIST CIFAR-10 CIFAR-100

Follow for updates

Join SOTA2 Contact