FBNetV5-AR-CLS

Reported on 5 benchmarks across 3 tasks · 1 paper

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

Methodology4 results

Neural Architecture SearchonImageNet
Accuracy· 2021-11-19
77.2
best: 83.9 (DeepMAD-50M)
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run arXiv:2111.10007
Neural Architecture SearchonImageNet
Top-1 Error Rate· 2021-11-19
22.8
best: 16.1 (DeepMAD-50M)
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run arXiv:2111.10007
AutoMLonImageNet
Accuracy· 2021-11-19
77.2
best: 83.9 (DeepMAD-50M)
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run arXiv:2111.10007
AutoMLonImageNet
Top-1 Error Rate· 2021-11-19
22.8
best: 16.1 (DeepMAD-50M)
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run arXiv:2111.10007

Computer Vision1 result

Image ClassificationonImageNet
GFLOPs· 2021-11-19
0.215
best: 1478 (InternImage-H)
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run arXiv:2111.10007