BigNASModel-M

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Methodology4 results

Neural Architecture SearchonImageNet
Top-1 Error Rate· 2020-03-24
21.1
best: 16.1 (DeepMAD-50M)
SOTA
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models arXiv:2003.11142
AutoMLonImageNet
Top-1 Error Rate· 2020-03-24
21.1
best: 16.1 (DeepMAD-50M)
SOTA
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models arXiv:2003.11142
Neural Architecture SearchonImageNet
Accuracy· 2020-03-24
78.9
best: 83.9 (DeepMAD-50M)
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models arXiv:2003.11142
AutoMLonImageNet
Accuracy· 2020-03-24
78.9
best: 83.9 (DeepMAD-50M)
BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models arXiv:2003.11142