Papers › Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

14 Dec 2018arXiv:1812.05836archive 2025-07-28

Martin Mundt, Sagnik Majumder, Tobias Weis, Visvanathan Ramesh

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.

PaperPDFCode

Code

MrtnMndt/Rethinking_CNN_Layerwise_Feature_Amounts officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

General ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections