Pseudo-Inverted Bottleneck Convolution for DARTS Search Space

1 code implementation • 31 Dec 2022 • Arash Ahmadian, Louis S. P. Liu, Yue Fei, Konstantinos N. Plataniotis, Mahdi S. Hosseini

Our proposed architecture is much less sensitive to evaluation layer count and outperforms a DARTS network with similar size significantly, at layer counts as small as 2.

Neural Architecture Search