Efficient ResNets: Residual Network Design
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 8 references that are in the map. First posted on arXiv 21 Jun 2023.
Builds on
6 of 8 references.
References · 6
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2019Lookahead Optimizer: k steps forward, 1 step backcited by 336
- 2021Go Wider Instead of Deepercited by 57
Built on by
Not cited yet.