# Efficient ResNets: Residual Network Design

Source: [Efficient ResNets: Residual Network Design](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475d9>)

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

Data updated: 2025-10-28T13:56:59.599Z

Authors: Aditya Thakur, Harish Chauhan, Nikunj Gupta

Published: 2023-06-21T08:28:51.000Z

## Abstract

ResNets (or Residual Networks) are one of the most commonly used models for image classification tasks. In this project, we design and train a modified ResNet model for CIFAR-10 image classification. In particular, we aimed at maximizing the test accuracy on the CIFAR-10 benchmark while keeping the size of our ResNet model under the specified fixed budget of 5 million trainable parameters. Model size, typically measured as the number of trainable parameters, is important when models need to be stored on devices with limited storage capacity (e.g. IoT/edge devices). In this article, we present our residual network design which has less than 5 million parameters. We show that our ResNet achieves a test accuracy of 96.04% on CIFAR-10 which is much higher than ResNet18 (which has greater than 11 million trainable parameters) when equipped with a number of training strategies and suitable ResNet hyperparameters. Models and code are available at https://github.com/Nikunj-Gupta/Efficient\_ResNets.

## 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/2306.12100>)

[PDF](<https://arxiv.org/pdf/2306.12100.pdf>)