Overfeat

Integrated recognition, localization and detection using convolutional networks

Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Robert Fergus, Yann LeCun

Research output: Contribution to conferencePaper

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.

Original languageEnglish (US)
StatePublished - Jan 1 2014
Event2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada
Duration: Apr 14 2014Apr 16 2014

Conference

Conference2nd International Conference on Learning Representations, ICLR 2014
CountryCanada
CityBanff
Period4/14/144/16/14

Fingerprint

learning
confidence
Localization
Deep learning
Boundary Objects
Confidence

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Education
  • Computer Science Applications

Cite this

Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2014). Overfeat: Integrated recognition, localization and detection using convolutional networks. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.

Overfeat : Integrated recognition, localization and detection using convolutional networks. / Sermanet, Pierre; Eigen, David; Zhang, Xiang; Mathieu, Michael; Fergus, Robert; LeCun, Yann.

2014. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.

Research output: Contribution to conferencePaper

Sermanet, P, Eigen, D, Zhang, X, Mathieu, M, Fergus, R & LeCun, Y 2014, 'Overfeat: Integrated recognition, localization and detection using convolutional networks' Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada, 4/14/14 - 4/16/14, .
Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. Overfeat: Integrated recognition, localization and detection using convolutional networks. 2014. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.
Sermanet, Pierre ; Eigen, David ; Zhang, Xiang ; Mathieu, Michael ; Fergus, Robert ; LeCun, Yann. / Overfeat : Integrated recognition, localization and detection using convolutional networks. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.
@conference{283f69593f6a4a8bb0a14a67e221955d,
title = "Overfeat: Integrated recognition, localization and detection using convolutional networks",
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.",
author = "Pierre Sermanet and David Eigen and Xiang Zhang and Michael Mathieu and Robert Fergus and Yann LeCun",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
note = "2nd International Conference on Learning Representations, ICLR 2014 ; Conference date: 14-04-2014 Through 16-04-2014",

}

TY - CONF

T1 - Overfeat

T2 - Integrated recognition, localization and detection using convolutional networks

AU - Sermanet, Pierre

AU - Eigen, David

AU - Zhang, Xiang

AU - Mathieu, Michael

AU - Fergus, Robert

AU - LeCun, Yann

PY - 2014/1/1

Y1 - 2014/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85070905768&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070905768&partnerID=8YFLogxK

M3 - Paper

ER -