Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

Code

• github.com/MrtnMndt/Rethinking_CNN_Layerwise_Feature_Amounts
  OfficialIn paperpytorch★ 0

Abstract

We characterize convolutional neural networks with respect to the relative amount of features per layer. Using a skew normal distribution as a parametrized framework, we investigate the common assumption of monotonously increasing feature-counts with higher layers of architecture designs. Our evaluation on models with VGG-type layers on the MNIST, Fashion-MNIST and CIFAR-10 image classification benchmarks provides evidence that motivates rethinking of our common assumption: architectures that favor larger early layers seem to yield better accuracy.

Tasks

Reproductions