Papperoni

2014

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

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

Open PDF Google Scholar

citations

Cite Score

96

AI summary

This paper introduces R-CNN, a detection algorithm combining convolutional neural networks (CNNs) with bottom-up region proposals, achieving a 30% improvement in mean average precision (mAP) on PASCAL VOC 2012 and outperforming OverFeat on the ILSVRC2013 dataset.

Main Contributions

Proposed R-CNN, a simple and scalable detection algorithm.
Combined high-capacity convolutional neural networks (CNNs) with bottom-up region proposals for object localization and segmentation.
Demonstrated that supervised pre-training on an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost when labeled training data is scarce.
Achieved a mean average precision (mAP) of 53.3% on PASCAL VOC 2012, a 30% improvement over the previous best result.
Outperformed OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset.

Abstract

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012-achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

Citation Graph

Loading graph...

References [40]

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]Gradient-Based Learning Applied to Document Recognition

Yann Lecun, Leon Bottou, Yoshua Bengio, Patrick Haffner - 1998

62 papers in library cite

I absolutely hated this paper. Has ~50 pages but seems like 200 pages. Takes too long to explain some things that really is just repeating itself. Also doesn't seem to add too much on top of LeNet-5. Also, focuses a lot on GTNs, which really didn't stick.

[5]Learning Internal Representations by Error Propagation

D. E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams - 1986

46 papers in library cite

I expected very little of this, but was so good in explaining concepts! Very good read. It gets a bit boring when it starts explaining things by the end of the chapter, but good nonetheless.

[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]Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position

Kunihiko Fukushima - 1980

8 papers in library cite

Good read! First conv net? :)

[10]Neural Network-Based Face Detection

H. Rowley, S. Baluja, Takeo Kanade - 1998

4 papers in library cite

It's nice, but nothing crazy. Just applying CNNs

[11]DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition

J. Donahue, Y. Jia, Oriol Vinyals, J. Hoffman, N. Zhang, E. Tzeng, Trevor Darrell - 2014

15 papers in library cite

Very nice paper. First I've seen (and based on the text, first ever) about feature extraction for images. It's very nice to see embeddings doing SotA

[12]Adaptive Deconvolutional Networks for Mid and High Level Feature Learning

M. Zeiler, G. Taylor, Rob Fergus - 2011

2 papers in library cite

The idea is very nice but I think this is soooo poorly explained. I had to ask AI to explain it to me - isn't that crazy? It isn't even a hard concept!

[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]Learning Hierarchical Features for Scene Labeling

Clement Farabet, C. Couprie, L. Najman, Yann Lecun - 2013

6 papers in library cite

Cited by deep learning paper (and 4 more)

Missing year

[15]ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC2012)

J. Deng, A. Berg, S. Satheesh, H. Su, A. Khosla, Li Fei Fei

1 paper in library cites

Imagenet dataset challenge paper

[16]Histograms of Oriented Gradients for Human Detection

N. Dalal, B. Triggs - 2005

12 papers in library cite

[17]Distinctive Image Features From Scale-Invariant Keypoints

D. Lowe - 2004

9 papers in library cite

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

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

8 papers in library cite

[19]Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

Aude Oliva, Antonio Torralba - 2001

7 papers in library cite

[20]Selective Search for Object Recognition

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

6 papers in library cite

[21]Deep Neural Networks for Object Detection

Christian Szegedy, A. Toshev, Dumitru Erhan - 2013

4 papers in library cite

[22]Diagnosing Error in Object Detectors

D. Hoiem, Y. Chodpathumwan, Q. Dai - 2012

4 papers in library cite

[23]Original Approach for the Localisation of Objects in Images

R. Vaillant, C. Monrocq, Yann Lecun - 1994

4 papers in library cite

[24]Pedestrian Detection With Unsupervised Multi-Stage Feature Learning

P. Sermanet, Koray Kavukcuoglu, S. Chintala, Yann Lecun - 2013

4 papers in library cite

[25]Semantic Segmentation With Second-Order Pooling

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

4 papers in library cite

[26]Example-Based Learning for View-Based Human Face Detection

K. Sung, T. Poggio - 1994

3 papers in library cite

[27]Category Independent Object Proposals

I. Endres, D. Hoiem - 2010

2 papers in library cite

[28]CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts

J. Carreira, C. Sminchisescu - 2012

2 papers in library cite

[29]Evaluation of Gist Descriptors for Web-Scale Image Search

M. Douze, Hervé Jégou, H. Sandhawalia, L. Amsaleg, Cordelia Schmid - 2009

2 papers in library cite

[30]Histograms of Sparse Codes for Object Detection

Xiang Ren, D. Ramanan - 2013

2 papers in library cite

[31]Measuring the Objectness of Image Windows

B. Alexe, T. Deselaers, V. Ferrari - 2012

2 papers in library cite

[32]Multiscale combinatorial Grouping

P. Arbelaez, J. P. Tuset, J. Barron, F. Marques, Jitendra Malik - 2014

2 papers in library cite

[33]Regionlets for Generic Object Detection

Xinpeng Wang, Michael Yang, S. Zhu, Yutong Lin - 2013

2 papers in library cite

[34]Scalable Multi-Label Annotation

J. Deng, O. Russakovsky, J. Krause, M. Bernstein, A. C. Berg, Li Fei Fei - 2014

2 papers in library cite

[35]Bottom-Up Segmentation for Top-Down Detection

Sanja Fidler, R. Mottaghi, A. Yuille, R. Urtasun - 2013

1 paper in library cites

[36]Crowdsourcing Annotations for Visual Object Detection

H. Su, J. Deng, Li Fei Fei - 2012

1 paper in library cites

[37]Fast, Accurate Detection of 100,000 Object Classes on a Single Machine

T. Dean, M. A. Ruzon, M. Segal, J. Shlens, S. Vijayanarasimhan, J. Yagnik - 2013

1 paper in library cites

[38]Mitosis Detection in Breast Cancer Histology Images With Deep Neural Networks

Dan C. Ciresan, A. Giusti, L. Gambardella, Jürgen Schmidhuber - 2013

1 paper in library cites

[39]Semantic Segmentation Using Regions and Parts

P. Arbelaez, B. Hariharan, C. Gu, S. Gupta, L. Bourdev, Jitendra Malik - 2012

1 paper in library cites

[40]Sketch Tokens: A Learned Mid-Level Representation for Contour and Object Detection

J. Lim, C. Zitnick, Piotr Dollar - 2013

1 paper in library cites

Cited by

18

papers in your library

Cites

15

papers in your library

Read

on July 31, 2025

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

Tags

Paper Aliases

No aliases