kMobileNet V3 Large 16ch

Reported on 3 benchmarks across 1 task

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

Computer Vision3 results

Image ClassificationonCIFAR-10
Percentage correct
92.74
best: 99.5 (ViT-H/14)
Image ClassificationonOxford-IIIT Pet Dataset
Accuracy
60.4
best: 99.6 (OmniVec2)
Image ClassificationonCIFAR-100
Percentage correct· uses extra data
71.36
best: 96.08 (EffNet-L2 (SAM))