Fast R-CNN

Ross Girshick
4/30/2015
cs.CV

Official code: rbgirshick/fast-rcnn (3,465 stars, last commit 2018-01-23).

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.

View on arXivView PDF

Code Implementations(1)

rbgirshick/fast-rcnnOfficial100%

Fast R-CNN

3,4651,562Shell, MATLABApr 1, 20158 years agoNOASSERTION

Cite this paper

@article{girshick2015fast,
  title  = {Fast R-CNN},
  author = {Ross Girshick},
  year   = {2015},
  eprint = {1504.08083},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1504.08083}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1504.08083.svg)](https://codeofpaper.com/paper/1504.08083)

Discussion