# Adaptive Convolution Kernel for Artificial Neural Networks

Source: [Adaptive Convolution Kernel for Artificial Neural Networks](<https://www.sota2.com/research/paper/68fa68531e209131cea1b826>)

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

Data updated: 2025-10-25T22:35:00.393Z

Authors: F. Boray Tek, \\.Ilker \\c{C}am, Deniz Karl{\\i}

Published: 2020-09-14T12:36:50.000Z

## Abstract

Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3$\\times$3) kernels. This paper describes a method for training the size of convolutional kernels to provide varying size kernels in a single layer. The method utilizes a differentiable, and therefore backpropagation-trainable Gaussian envelope which can grow or shrink in a base grid. Our experiments compared the proposed adaptive layers to ordinary convolution layers in a simple two-layer network, a deeper residual network, and a U-Net architecture. The results in the popular image classification datasets such as MNIST, MNIST-CLUTTERED, CIFAR-10, Fashion, and \`\`Faces in the Wild'' showed that the adaptive kernels can provide statistically significant improvements on ordinary convolution kernels. A segmentation experiment in the Oxford-Pets dataset demonstrated that replacing a single ordinary convolution layer in a U-shaped network with a single 7$\\times$7 adaptive layer can improve its learning performance and ability to generalize.

## 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/2009.06385>)

[PDF](<https://arxiv.org/pdf/2009.06385.pdf>)
