Preprint · 2022 · Open access
Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models
arXiv (Cornell University) · Published 23 May 2022 · DOI 10.48550/arxiv.2205.12050
In brief
“Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models” is a 2022 preprint by Sabeesh Ethiraj and Bharath Kumar Bolla, published in arXiv (Cornell University). OpenAlex counts 5 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 5
- Most cited in
- 2025 (2)
- References
- 17
- Authors
- 2
Abstract
Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. Many techniques have evolved over the past decade that made models lighter, faster, and robust with better generalization. However, many deep learning practitioners persist with pre-trained models and architectures trained mostly on standard datasets such as Imagenet, MS-COCO, IMDB-Wiki Dataset, and Kinetics-700 and are either hesitant or unaware of redesigning the architecture from scratch that will lead to better performance. This scenario leads to inefficient models that are not suitable on various devices such as mobile, edge, and fog. In addition, these conventional training methods are of concern as they consume a lot of computing power. In this paper, we revisit various SOTA techniques that deal with architecture efficiency (Global Average Pooling, depth-wise convolutions & squeeze and excitation, Blurpool), learning rate (Cyclical Learning Rate), data augmentation (Mixup, Cutout), label manipulation (label smoothing), weight space manipulation (stochastic weight averaging), and optimizer (sharpness aware minimization). We demonstrate how an efficient deep convolution network can be built in a phased manner by sequentially reducing the number of training parameters and using the techniques mentioned above. We achieved a SOTA accuracy of 99.2% on MNIST data with just 1500 parameters and an accuracy of 86.01% with just over 140K parameters on the CIFAR-10 dataset.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ethiraj, S., & Bolla, B. K. (2022). Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.12050
MLA 9
Ethiraj, Sabeesh, and Bharath Kumar Bolla. “Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2205.12050.
Chicago
Ethiraj, Sabeesh and Bharath Kumar Bolla. 2022. “Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.12050.
Harvard
Ethiraj, S. and Bolla, B. K. (2022) ‘Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models’, arXiv (Cornell University). doi:10.48550/arxiv.2205.12050.
IEEE
S. Ethiraj and B. K. Bolla, “Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2205.12050.
BibTeX
@misc{ethiraj2022training,
title = {{Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models}},
author = {Ethiraj, Sabeesh and Bolla, Bharath Kumar},
howpublished = {arXiv (Cornell University)},
year = {2022},
doi = {10.48550/arxiv.2205.12050},
url = {https://doi.org/10.48550/arxiv.2205.12050}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 1 | |
| 2023 | 1 | |
| 2025 | 2 | |
| 2026 | 1 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- model compression
- lightweight neural networks
- global average pooling
- depthwise separable convolution
- squeeze-and-excitation
- cyclical learning rate
- mixup
- cutouts
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Ethiraj, S., & Bolla, B. K. (2022). Training Efficient CNNS: Tweaking the Nuts and Bolts of Neural Networks for Lighter, Faster and Robust Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.12050
How many times has this paper been cited?
5 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Sabeesh Ethiraj, Bharath Kumar Bolla.
What is the DOI of this paper?
10.48550/arxiv.2205.12050, permanently at https://doi.org/10.48550/arxiv.2205.12050. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.