# Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

Source: [Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures](<https://www.sota2.com/research/paper/68fa652e1e209131cea08a1a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:19:52.933Z

Authors: Martin Mundt, Sagnik Majumder, Tobias Weis, Visvanathan Ramesh

Published: 2018-12-14T09:28:05.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.05836>)

[PDF](<https://arxiv.org/pdf/1812.05836.pdf>)