Convolutional Neural Networks


Introduced by Radosavovic et al. in Designing Network Design Spaces

RegNetX is a convolutional network design space with simple, regular models with parameters: depth $d$, initial width $w_{0} > 0$, and slope $w_{a} > 0$, and generates a different block width $u_{j}$ for each block $j < d$. The key restriction for the RegNet types of model is that there is a linear parameterisation of block widths (the design space only contains models with this linear structure):

$$ u_{j} = w_{0} + w_{a}\cdot{j} $$

For RegNetX we have additional restrictions: we set $b = 1$ (the bottleneck ratio), $12 \leq d \leq 28$, and $w_{m} \geq 2$ (the width multiplier).

Source: Designing Network Design Spaces


Paper Code Results Date Stars


Task Papers Share
Ensemble Learning 1 25.00%
Medical Object Detection 1 25.00%
Object Detection 1 25.00%
Image Classification 1 25.00%