MoGA uses weighted NSGA-II and a one-shot supernet to search mobile GPU-aware architectures, producing models that beat MobileNetV3 on ImageNet at similar mobile GPU latency with 200x less search cost than MnasNet.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MoGA: Searching Beyond MobileNetV3
MoGA uses weighted NSGA-II and a one-shot supernet to search mobile GPU-aware architectures, producing models that beat MobileNetV3 on ImageNet at similar mobile GPU latency with 200x less search cost than MnasNet.