ResNet-152x4-AGC (ImageNet-21K)

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonOxford-IIIT Pet Dataset
Accuracy· 2021-05-31
93.21
best: 99.6 (OmniVec2)
SOTA
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images arXiv:2106.00116
Image ClassificationonCIFAR-10
Percentage correct· 2021-05-31
97.82
best: 99.5 (ViT-H/14)
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images arXiv:2106.00116
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2021-05-31
99.49
best: 99.76 (CCT-14/7x2)
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images arXiv:2106.00116
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-05-31
88.54
best: 96.08 (EffNet-L2 (SAM))
Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images arXiv:2106.00116