Papperoni

2015

Fast R-CNN

Ross Girshick

Open PDF Google Scholar

citations

Cite Score

96

AI summary

This paper introduces the Fast R-CNN object detection method, which classifies object proposals using deep convolutional networks, trains the VGG16 network 9x faster than R-CNN, is 213x faster at test-time, and achieves a higher mAP on PASCAL VOC 2012.

Main Contributions

Proposes Fast R-CNN, a fast region-based convolutional network for object detection.
Achieves higher detection quality (mAP) than R-CNN and SPPnet.
Introduces a single-stage training approach using a multi-task loss.
Enables training to update all network layers.
Eliminates the need for disk storage for feature caching.

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 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012. Compared to SPPnet, Fast R-CNN trains VGG16 3× faster, tests 10× 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.

Citation Graph

Loading graph...

References [25]

Sort:

Filter:

[1]Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, Andrew Zisserman - 2014

20 papers in library cite

This is very good! The great thing here is small filters and depth analysis, but truly they do some other stuff as well: SotA, generalization for other tasks, and open source their models. Very nice.

[2]ImageNet Classification With Deep Convolutional Neural Networks

Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton - 2012

71 papers in library cite

I'm giving this a 5 just because of the impact, but this is VEEERY derivative of earlier work. Kudos for them for putting it all together, but really there's nothing revolutionary here.

[3]ImageNet: A Large-Scale Hierarchical Image Database

J. Deng, W. Dong, Richard Socher, L. J. Li, K. Li, Li Fei Fei - 2009

28 papers in library cite

Very nice idea and huge impact!

[4]Microsoft COCO: Common Objects in Context

T. Y. Lin, M. Maire, S. Belongie, James Hays, Pietro Perona, D. Ramanan, Piotr Dollar, C. L. Zitnick - 2014

14 papers in library cite

I liked this paper a lot. It's a bit long and I was already a bit tired, but it was nice overall.

[5]Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Ross Girshick, J. Donahue, Trevor Darrell, Jitendra Malik - 2014

18 papers in library cite

Good results, beat overfeat, used pretraining for improving performance. Only issue is that the paper is overly long...

[6]The PASCAL Visual Object Classes (VOC) Challenge

Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman - 2010

7 papers in library cite

Good overview of the VOC challenge and good read, but too long and the part that they describe methods and results is very boring. Also, not related to NNs at the time!

[7]Backpropagation Applied to Handwritten Zip-Code Recognition

Yann Lecun, B. Boser, John S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackal - 1989

24 papers in library cite

The first convolution NN! Very simple concept and very simply explained. Very good results and overall a good read.

[8]Caffe: Convolutional Architecture for Fast Feature Embedding

Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, Ross Girshick, S. Guadarrama, Trevor Darrell - 2014

12 papers in library cite

Nothing new really, but worth the read. It's nice because it's the precursor to current AI frameworks + has a Python interface. Also good that model representation is separate from implementation

[9]Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

K. He, X. Zhang, S. Ren, Jian Sun - 2014

6 papers in library cite

Very simple, general and effective method. The paper ends at page ~4 TBH, the rest is just results and gets boring. Good contribution though.

[10]Multitask Learning

Rich Caruana - 1997

13 papers in library cite

I expected waaaaaay more from this paper. The idea is sooooo simple and the results are underwhelming. Also, 30 pages for something that could be said in 10. The writing style is a bit boring. TBH it seems like it's just a re-writing of Caruana's PhD thesis.

[11]Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce - 2006

14 papers in library cite

It's a fun read, but in the end is just an application of the spatial pyramid matching kernel from the other paper.

[12]Network in Network

M. Lin, Qinlang Chen, Shuicheng Yan - 2013

11 papers in library cite

I think this was badly written and explained. The idea is nice but I didn't like the paper at all.

[13]OverFeat: Integrated Recognition, Localization and Detection Using Convolutional Networks

P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, Rob Fergus, Yann Lecun - 2014

16 papers in library cite

Very convoluted method, was SotA for only a bit of time, and the paper is very boring.

[14]Return of the Devil in the Details: Delving Deep Into Convolutional Nets

K. Chatfield, K. Simonyan, A. Vedaldi, Andrew Zisserman - 2014

5 papers in library cite

Using CNNs as feature extractors

[15]Rapid Object Detection Using a Boosted Cascade of Simple Features

P. Viola, M. J. Jones - 2001

10 papers in library cite

[16]Object Detection With Discriminatively Trained Part-Based Models

P. F. Felzenszwalb, Ross Girshick, D. Mcallester, D. Ramanan - 2010

8 papers in library cite

[17]Selective Search for Object Recognition

J. Uijlings, K. V. D. Sande, T. Gevers, A. Smeulders - 2013

6 papers in library cite

[18]Scalable Object Detection Using Deep Neural Networks

Dumitru Erhan, Christian Szegedy, A. Toshev, Dragomir Anguelov - 2014

4 papers in library cite

[19]Semantic Segmentation With Second-Order Pooling

J. Carreira, R. Caseiro, J. Batista, C. Sminchisescu - 2012

4 papers in library cite

[20]Do We Need More Training Data or Better Models for Object Detection?

X. Zhu, C. Vondrick, D. Ramanan, C. Fowlkes - 2012

2 papers in library cite

[21]What Makes for Effective Detection Proposals?

J. H. Hosang, R. Benenson, Piotr Dollar, B. Schiele - 2015

2 papers in library cite

[22]Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation

E. Denton, Wojciech Zaremba, J. Bruna, Yann Lecun, Rob Fergus - 2014

1 paper in library cites

[23]Region-Based Convolutional Networks for Accurate Object Detection and Segmentation

Ross Girshick, J. Donahue, Trevor Darrell, Jitendra Malik - 2015

1 paper in library cites

[24]Restructuring of Deep Neural Network Acoustic Models With Singular Value Decomposition

J. Xue, Jeffrey Li, Y. Gong - 2013

1 paper in library cites

[25]segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

Yuxuan Zhu, R. Urtasun, Ruslan Salakhutdinov, Sanja Fidler - 2015

1 paper in library cites

Cited by

2

papers in your library

Cites

14

papers in your library

Read

on October 20, 2025

Very nice improvement over R-CNN! I like that they start pushing towards having an end-to-end framework, but this still falls short for using a separate region proposal module.

Tags

Paper Aliases

No aliases