CIFAR-100
Unknown
60K 32x32 color images in 100 fine-grained classes grouped into 20 superclasses. More challenging than CIFAR-10.
Benchmark Stats
Models4
Papers4
Metrics1
SOTA History
Coming SoonVisual timeline of state-of-the-art progression over time will appear here.
accuracy
accuracy
Higher is better
| Rank | Model | Code | Score | Paper / Source |
|---|---|---|---|---|
| 1 | vit-h-14 Fine-tuned from ImageNet pretraining. | 94.55 | google-research | |
| 2 | efficientnet-b7 Transfer learning from ImageNet. | 91.7 | google-research | |
| 3 | vit-b-16 Fine-tuned from ImageNet-21K. | 91.48 | huggingface | |
| 4 | resnet-50 With Cutout augmentation. | 78.04 | cutout-paper |