NSGANetV2-m

Reported on 4 benchmarks across 2 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· 2020-07-20
78.3
best: 83.9 (DeepMAD-50M)
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search arXiv:2007.10396
Neural Architecture SearchonImageNet
Top-1 Error Rate· 2020-07-20
21.7
best: 16.1 (DeepMAD-50M)
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search arXiv:2007.10396
AutoMLonImageNet
Accuracy· 2020-07-20
78.3
best: 83.9 (DeepMAD-50M)
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search arXiv:2007.10396
AutoMLonImageNet
Top-1 Error Rate· 2020-07-20
21.7
best: 16.1 (DeepMAD-50M)
NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search arXiv:2007.10396