Preprint · 2013 · Open access

Some Improvements on Deep Convolutional Neural Network Based Image Classification

Andrew Howard

arXiv (Cornell University) · Published 19 December 2013 · DOI 10.48550/arxiv.1312.5402

Free PDFView at the publisherCite this paper

In brief

“Some Improvements on Deep Convolutional Neural Network Based Image Classification” is a 2013 preprint by Andrew Howard, published in arXiv (Cornell University). OpenAlex counts 443 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
443
Most cited in
2019 (66)
References
8
Authors
1

Abstract

We investigate multiple techniques to improve upon the current state of the art deep convolutional neural network based image classification pipeline. The techiques include adding more image transformations to training data, adding more transformations to generate additional predictions at test time and using complementary models applied to higher resolution images. This paper summarizes our entry in the Imagenet Large Scale Visual Recognition Challenge 2013. Our system achieved a top 5 classification error rate of 13.55% using no external data which is over a 20% relative improvement on the previous year's winner.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Howard, A. (2013). Some Improvements on Deep Convolutional Neural Network Based Image Classification. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1312.5402

MLA 9

Howard, Andrew. “Some Improvements on Deep Convolutional Neural Network Based Image Classification.” arXiv (Cornell University), 2013. https://doi.org/10.48550/arxiv.1312.5402.

Chicago

Howard, Andrew. 2013. “Some Improvements on Deep Convolutional Neural Network Based Image Classification.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1312.5402.

Harvard

Howard, A. (2013) ‘Some Improvements on Deep Convolutional Neural Network Based Image Classification’, arXiv (Cornell University). doi:10.48550/arxiv.1312.5402.

IEEE

A. Howard, “Some Improvements on Deep Convolutional Neural Network Based Image Classification,” arXiv (Cornell University), 2013, doi: 10.48550/arxiv.1312.5402.

BibTeX

@misc{howard2013some,
  title     = {{Some Improvements on Deep Convolutional Neural Network Based Image Classification}},
  author    = {Howard, Andrew},
  howpublished = {arXiv (Cornell University)},
  year      = {2013},
  doi       = {10.48550/arxiv.1312.5402},
  url       = {https://doi.org/10.48550/arxiv.1312.5402}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20174848
20184444
20196666
20205555
20216262
20225555
20231919
20242020
20252020
202644

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • image classification
  • deep convolutional neural networks
  • ImageNet
  • data augmentation
  • image transformation
  • ensemble learning
  • high-resolution imagery

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Howard, A. (2013). Some Improvements on Deep Convolutional Neural Network Based Image Classification. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1312.5402

How many times has this paper been cited?

443 times, according to OpenAlex on 15 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: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Andrew Howard.

What is the DOI of this paper?

10.48550/arxiv.1312.5402. The permanent link is https://doi.org/10.48550/arxiv.1312.5402.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.