Preprint · 2015 · Open access

Fast R-CNN

Ross Girshick

arXiv (Cornell University) · Published 30 April 2015 · DOI 10.48550/arxiv.1504.08083

Free PDFView at the publisherCite this paper

In brief

“Fast R-CNN” is a 2015 preprint by Ross Girshick, published in arXiv (Cornell University). OpenAlex counts 2,813 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
2,813
Most cited in
2018 (447)
References
24
Authors
1

Abstract

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compared to previous work, Fast R-CNN employs several innovations to improve training and testing speed while also increasing detection accuracy. Fast R-CNN trains the very deep VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3x faster, tests 10x faster, and is more accurate. Fast R-CNN is implemented in Python and C++ (using Caffe) and is available under the open-source MIT License at https://github.com/rbgirshick/fast-rcnn.

Cite this paper

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

APA 7

Girshick, R. (2015). Fast R-CNN. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1504.08083

MLA 9

Girshick, Ross. “Fast R-CNN.” arXiv (Cornell University), 2015. https://doi.org/10.48550/arxiv.1504.08083.

Chicago

Girshick, Ross. 2015. “Fast R-CNN.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1504.08083.

Harvard

Girshick, R. (2015) ‘Fast R-CNN’, arXiv (Cornell University). doi:10.48550/arxiv.1504.08083.

IEEE

R. Girshick, “Fast R-CNN,” arXiv (Cornell University), 2015, doi: 10.48550/arxiv.1504.08083.

BibTeX

@misc{girshick2015fast,
  title     = {{Fast R-CNN}},
  author    = {Girshick, Ross},
  howpublished = {arXiv (Cornell University)},
  year      = {2015},
  doi       = {10.48550/arxiv.1504.08083},
  url       = {https://doi.org/10.48550/arxiv.1504.08083}
}

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

Citations by year

YearCitationsShare of the best year
2017312312
2018447447
2019405405
2020417417
2021373373
20229191
2023156156
2024156156
2025188188
20269696

Topic and keywords

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

  • object detection
  • Fast R-CNN
  • object proposals
  • VGG16
  • training speed
  • detection accuracy
  • Pascal VOC 2012

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?

Girshick, R. (2015). Fast R-CNN. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1504.08083

How many times has this paper been cited?

2,813 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?

Ross Girshick.

What is the DOI of this paper?

10.48550/arxiv.1504.08083. The permanent link is https://doi.org/10.48550/arxiv.1504.08083.

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.