EfficientNetV2-L

Reported on 5 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 Vision5 results

Image ClassificationonStanford Cars
Accuracy· 2021-04-01
95.1
best: 96.868 (efficient adaptive ensembling)
SOTA
EfficientNetV2: Smaller Models and Faster Training arXiv:2104.00298
Image ClassificationonCIFAR-10
Percentage correct· uses extra data· 2021-04-01
99.1
best: 99.5 (ViT-H/14)
EfficientNetV2: Smaller Models and Faster Training arXiv:2104.00298
Image ClassificationonFlowers-102
Accuracy· uses extra data· 2021-04-01
98.8
best: 99.76 (CCT-14/7x2)
EfficientNetV2: Smaller Models and Faster Training arXiv:2104.00298
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2021-04-01
92.3
best: 96.08 (EffNet-L2 (SAM))
EfficientNetV2: Smaller Models and Faster Training arXiv:2104.00298
Image ClassificationonImageNet
GFLOPs· 2021-04-01
53
best: 1478 (InternImage-H)
EfficientNetV2: Smaller Models and Faster Training arXiv:2104.00298