# Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach

Source: [Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach](<https://www.sota2.com/research/paper/68fa797e1e209131cea7dc94>)

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

Data updated: 2025-10-26T04:58:48.249Z

Authors: Shreyas Rajeev, B Sathish Babu

Published: 2025-06-16T15:15:30.000Z

## Abstract

Kernel size selection in Convolutional Neural Networks (CNNs) is a critical but often overlooked design decision that affects receptive field, feature extraction, computational cost, and model accuracy. This paper proposes the Best Kernel Size Estimation Function (BKSEF), a mathematically grounded and empirically validated framework for optimal, layer-wise kernel size determination. BKSEF balances information gain, computational efficiency, and accuracy improvements by integrating principles from information theory, signal processing, and learning theory. Extensive experiments on CIFAR-10, CIFAR-100, ImageNet-lite, ChestX-ray14, and GTSRB datasets demonstrate that BKSEF-guided architectures achieve up to 3.1 percent accuracy improvement and 42.8 percent reduction in FLOPs compared to traditional models using uniform 3x3 kernels. Two real-world case studies further validate the approach: one for medical image classification in a cloud-based setup, and another for traffic sign recognition on edge devices. The former achieved enhanced interpretability and accuracy, while the latter reduced latency and model size significantly, with minimal accuracy trade-off. These results show that kernel size can be an active, optimizable parameter rather than a fixed heuristic. BKSEF provides practical heuristics and theoretical support for researchers and developers seeking efficient and application-aware CNN designs. It is suitable for integration into neural architecture search pipelines and real-time systems, offering a new perspective on CNN optimization.

## 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/2506.14846>)

[PDF](<https://arxiv.org/pdf/2506.14846.pdf>)
