# Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices

Source: [Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices](<https://www.sota2.com/research/paper/68fa68ba1e209131cea1dcc1>)

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

Data updated: 2025-10-25T22:43:58.904Z

Authors: Sebastian M\\"uksch, Theo Olausson, John Wilhelm, Pavlos Andreadis

Published: 2020-05-11T09:54:54.000Z

## Abstract

Convolutional Neural Networks, or CNNs, are the state of the art for image classification, but typically come at the cost of a large memory footprint. This limits their usefulness in applications relying on embedded devices, where memory is often a scarce resource. Recently, there has been significant progress in the field of image classification on such memory-constrained devices, with novel contributions like the ProtoNN, Bonsai and FastGRNN algorithms. These have been shown to reach up to 98.2% accuracy on optical character recognition using MNIST-10, with a memory footprint as little as 6KB. However, their potential on more complex multi-class and multi-channel image classification has yet to be determined. In this paper, we compare CNNs with ProtoNN, Bonsai and FastGRNN when applied to 3-channel image classification using CIFAR-10. For our analysis, we use the existing Direct Convolution algorithm to implement the CNNs memory-optimally and propose new methods of adjusting the FastGRNN model to work with multi-channel images. We extend the evaluation of each algorithm to a memory size budget of 8KB, 16KB, 32KB, 64KB and 128KB to show quantitatively that Direct Convolution CNNs perform best for all chosen budgets, with a top performance of 65.7% accuracy at a memory footprint of 58.23KB.

## 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/2005.04968>)

[PDF](<https://arxiv.org/pdf/2005.04968.pdf>)