A global NAS method with a macro-micro split search and a dynamic training scheme reports competitive accuracy on several benchmarks and outperforms Adaface on TinyFace with smaller models.
”A genetic pro- gramming approach to designing convolutional neural network architectures.” Pro- ceedings of the genetic and evolutionary computation conference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Efficient Global Neural Architecture Search
A global NAS method with a macro-micro split search and a dynamic training scheme reports competitive accuracy on several benchmarks and outperforms Adaface on TinyFace with smaller models.