Cited by 28,105Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesVisual Attention and Saliency Detection

Fast R-CNN

Girshick, Ross·2015·2015 IEEE International Conference on Computer Vision (ICCV)

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.

Integrity signals

Registry

Crossref · 10.1109/iccv.2015.169

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Fast R-CNN significantly improves training time and inference time over R-CNN and also increases mAP.

    “Fast R-CNN [20] achieves a significant improvement in the model training time and inference time. Moreover, it also observes an increase in the performance matrix of the object detection i.e., mAP.”
  • Fast R-CNN with VGG-16 takes 320ms on 2000 SS proposals (or 223ms if using SVD on fully-connected layers).

    “Fast R-CNN with VGG-16 takes 320ms on 2000 SS proposals (or 223ms if using SVD on fully-connected layers [2]).”
  • On VOC07 dataset, Fast RCNN increased the mAP from 58.5% (RCNN) to 70.0% while with a detection speed over 200 times faster than R-CNN.

    “On VOC07 dataset, Fast RCNN increased the mAP from 58.5% (RCNN) to 70.0% while with a detection speed over 200 times faster than R-CNN.”

    From Object Detection in 20 Years: A Survey (2023) · cites this paper as [18]

  • Smooth L1 loss was proposed by combining the benefits of L1 loss and L2 loss.

    “Combining the benefits of L1 loss and L2 loss, the researchers propose Smooth L1 loss [18]”

    From Object Detection in 20 Years: A Survey (2023) · cites this paper as [18]

  • In the deep learning era, bootstrap was shortly discarded in object detection during 2014-2016.

    “In the deep learning era, due to the increase of computing power, bootstrap was shortly discarded in object detection during 2014-2016 [16-20].”

    From Object Detection in 20 Years: A Survey (2023) · cites this paper as [18]

Cites

Flagged first, then by citations

2 of the 29 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Girshick, R.
Affiliations
Microsoft (United States) (US)
Corresponding author
Girshick, Ross
Venue
2015 IEEE International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2015-12
Pages
1440-1448
OpenAlex
W1536680647
Cited by
28,105
References
29
Citations by year
2026: 1553 · 2025: 3315 · 2024: 3957 · 2023: 3825 · 2022: 3371 · 2021: 3463 · 2020: 2956 · 2019: 2678 · 2018: 1649 · 2017: 932 · 2016: 371 · 2015: 30 · 2014: 1 · 2013: 1
FWCI
407.64
Type
conference paper
Language
en
Open access
closed
Locations
IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
object detection, Fast R-CNN, object proposals, VGG16, training speed, detection accuracy, Pascal VOC 2012

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review