Papperoni

2014

OverFeat: Integrated Recognition, Localization and Detection Using Convolutional Networks

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

Open PDF Google Scholar

citations

AI summary

This paper introduces an integrated framework using Convolutional Networks for classification, localization, and detection, winning the ImageNet 2013 localization task. It introduces a novel deep learning approach to localization by learning to predict object boundaries, achieving a new state-of-the-art for detection, and releases a feature extractor called OverFeat.

Main Contributions

Introduces an integrated framework for classification, localization, and detection using Convolutional Networks.
Presents a multiscale and sliding window approach efficiently implemented within a ConvNet.
Introduces a novel deep learning approach to localization by learning to predict object boundaries and accumulating bounding boxes.
Demonstrates that different tasks can be learned simultaneously using a single shared network.
Achieves state-of-the-art results in the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) localization task.

Abstract

We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 (ILSVRC2013) and obtained very competitive results for the detection and classifications tasks. In post-competition work, we establish a new state of the art for the detection task. Finally, we release a feature extractor from our best model called OverFeat.

Citation Graph

Loading graph...

References [29]

Sort:

Filter:

[1]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.

[2]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!

[3]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.

[4]Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors

Geoffrey E. Hinton, N. Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R. Salakhutdinov - 2012

25 papers in library cite

Dropout, super impactful. The idea that you are training many estimators at once is also very nice.

[5]Handwritten Digit Recognition With a Back-Propagation Network

Yann Lecun, B. Boser, John S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel - 1990

10 papers in library cite

Just a minor derivation of the previous paper, adding more layers to the net. Pretty much the same exact text than the other one. Uninteresting if you read the other.

[6]Multi-Column Deep Neural Networks for Image Classification

Dan C. Ciresan, Ueli Meier, Jürgen Schmidhuber - 2012

11 papers in library cite

Very nice paper! And I am impressed they used CNNs before Hinton's paper. It's a shame there are so few citations. They also propose max-pooling and actually give a good explanation about it.

[7]What Is the Best Multi-Stage Architecture for Object Recognition?

K. Jarrett, Koray Kavukcuoglu, Marc'aurelio Ranzato, Yann Lecun - 2009

20 papers in library cite

So boring and convoluted... They try to make things more abstract by saying "filter banks" and "2 stages", but in the end it's CNNs. It seems like they are trying to tie NNs to the rest of ML, but it doesn't work.

[8]Learning Methods for Generic Object Recognition With Invariance to Pose and Lighting

Yann Lecun, Fu Jie Huang, Leon Bottou - 2004

18 papers in library cite

Good paper, nice methodology for creating different images. However, I think that this was not too impactful... I don't see this being used a lot.

[9]Convolutional neural Networks Applied to House Numbers Digit Classification

P. Sermanet, S. Chintala, Yann Lecun - 2012

6 papers in library cite

This reads like an undergrad's research paper or a recent master's paper. Only applying stuff to a new dataset.

[10]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)

[11]Selective Search for Object Recognition

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

6 papers in library cite

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

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

4 papers in library cite

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

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

4 papers in library cite

[14]Synergistic Face Detection and Pose Estimation With Energy-Based Models

M. Osadchy, Yann Lecun, M. Miller - 2007

4 papers in library cite

[15]Toward Automatic Phenotyping of Developing Embryos From Videos

F. Ning, D. Delhomme, Yann Lecun, F. Piano, Leon Bottou, P. Barbano - 2005

4 papers in library cite

[16]Traffic Sign Recognition With Multi-Scale Convolutional Networks

P. Sermanet, Yann Lecun - 2011

4 papers in library cite

[17]Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection

C. Garcia, M. Delakis - 2004

3 papers in library cite

[18]Learning Long-Range Vision for Autonomous Off-Road Driving

Raia Hadsell, P. Sermanet, M. Scoffier, A. Erkan, K. Kavackuoglu, U. Muller, Yann Lecun - 2009

3 papers in library cite

[19]Category Independent Object Proposals

I. Endres, D. Hoiem - 2010

2 papers in library cite

[20]Reading Handwritten Digits: A Zip Code Recognition System

O. Matan, J. Bromley, C. Burges, John Denker, Lawrence Jackel, Yann Lecun, E. Pednault, W. Satterfield, C. Stenard, T. Thompson - 1992

2 papers in library cite

[21]Transforming Auto-Encoders

Geoffrey E. Hinton, Alex Krizhevsky, S. D. Wang - 2011

2 papers in library cite

[22]A Convolutional Neural Network Hand tracker

S. Nowlan, J. Platt - 1995

1 paper in library cites

[23]Fast Image Scanning With Deep Max-Pooling Convolutional Neural Networks

A. Giusti, Dan C. Ciresan, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber - 2013

1 paper in library cites

[24]Learning Invarance Through Imitation

G. Taylor, I. Spiro, C. Bregler, Rob Fergus - 2011

1 paper in library cites

[25]Object Recognition by Sequential Figure-Ground Ranking

J. Carreira, F. Li, C. Sminchisescu - 2012

1 paper in library cites

[26]Pose-Sensitive Embedding by Nonlinear Nca regression

G. Taylor, Rob Fergus, G. Williams, I. Spiro, C. Bregler - 2011

1 paper in library cites

[27]Prime Object Proposals With Randomized Prims algorithm

S. Manen, M. Guillaumin, Luc Van Gool - 2013

1 paper in library cites

Missing year

[28]Supervised Learning of Image Restoration With Convolutional Networks

V. Jain, J. F. Murray, F. Roth, S. Turaga, V. Zhigulin, K. Briggman, M. Helmstaedter, W. Denk, H. S. Seung

1 paper in library cites

[29]Text Detection With Convolutional Neural Networks

M. Delakis, C. Garcia - 2008

1 paper in library cites

Cited by

16

papers in your library

Cites

10

papers in your library

Read

on July 31, 2025

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

Tags

Paper Aliases

No aliases