Fast R-CNN

@article{Girshick2015FastR,
  title={Fast R-CNN},
  author={Ross B. Girshick},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={1440-1448}
}
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… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 4,893 CITATIONS

A Data Augmentation Strategy Based on Simulated Samples for Ship Detection in RGB Remote Sensing Images

VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Deep Learning Framework for Signal Detection and Modulation Classification

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Novel Effectively Optimized One-Stage Network for Object Detection in Remote Sensing Imagery

VIEW 7 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Survey of Deep Learning-Based Object Detection

VIEW 20 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Adaptive Brightness Learning for Active Object Recognition

  • Nuo Xu, Chunlei Huo, Chunhong Pan
  • Computer Science
  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Advances in scene understanding: object detection, reconstruction, layouts, and inference

VIEW 13 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

An Automatic Car Accident Detection Method Based on Cooperative Vehicle Infrastructure Systems

VIEW 13 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Attention CoupleNet: Fully Convolutional Attention Coupling Network for Object Detection

VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2020

CITATION STATISTICS

  • 1,510 Highly Influenced Citations

  • Averaged 1,419 Citations per year from 2017 through 2019

  • 13% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

ImageNet: A large-scale hierarchical image database

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Multitask Learning

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

What Makes for Effective Detection Proposals?

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

segDeepM: Exploiting segmentation and context in deep neural networks for object detection

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL