A few-shot NAS method that splits the search space by the number of nonlinear functions, halves channels per supernet, and balances sampling across supernets achieves strong results on NAS-Bench-201 and ImageNet.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions
A few-shot NAS method that splits the search space by the number of nonlinear functions, halves channels per supernet, and balances sampling across supernets achieves strong results on NAS-Bench-201 and ImageNet.