skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A mixed-scale dense convolutional neural network for image analysis

Abstract

We report that deep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results in practice, a large number of trainable parameters are often required. Here, we introduce a network architecture based on using dilated convolutions to capture features at different image scales and densely connecting all feature maps with each other. The resulting architecture is able to achieve accurate results with relatively few parameters and consists of a single set of operations, making it easier to implement, train, and apply in practice, and automatically adapts to different problems. Lastly, we compare results of the proposed network architecture with popular existing architectures for several segmentation problems, showing that the proposed architecture is able to achieve accurate results with fewer parameters, with a reduced risk of overfitting the training data.

Authors:
 [1];  [2]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Berkeley, CA (United States)
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21); USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); USDOE Office of Science (SC), Biological and Environmental Research (BER) (SC-23)
OSTI Identifier:
1414877
Alternate Identifier(s):
OSTI ID: 1485062
Grant/Contract Number:  
AC02-05CH11231; AC03-76SF00098
Resource Type:
Journal Article: Published Article
Journal Name:
Proceedings of the National Academy of Sciences of the United States of America
Additional Journal Information:
Journal Volume: 115; Journal Issue: 2; Journal ID: ISSN 0027-8424
Publisher:
National Academy of Sciences, Washington, DC (United States)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; image segmentation; machine learning; convolution neural networks

Citation Formats

Pelt, Daniël M., and Sethian, James A. A mixed-scale dense convolutional neural network for image analysis. United States: N. p., 2017. Web. doi:10.1073/pnas.1715832114.
Pelt, Daniël M., & Sethian, James A. A mixed-scale dense convolutional neural network for image analysis. United States. doi:10.1073/pnas.1715832114.
Pelt, Daniël M., and Sethian, James A. Tue . "A mixed-scale dense convolutional neural network for image analysis". United States. doi:10.1073/pnas.1715832114.
@article{osti_1414877,
title = {A mixed-scale dense convolutional neural network for image analysis},
author = {Pelt, Daniël M. and Sethian, James A.},
abstractNote = {We report that deep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results in practice, a large number of trainable parameters are often required. Here, we introduce a network architecture based on using dilated convolutions to capture features at different image scales and densely connecting all feature maps with each other. The resulting architecture is able to achieve accurate results with relatively few parameters and consists of a single set of operations, making it easier to implement, train, and apply in practice, and automatically adapts to different problems. Lastly, we compare results of the proposed network architecture with popular existing architectures for several segmentation problems, showing that the proposed architecture is able to achieve accurate results with fewer parameters, with a reduced risk of overfitting the training data.},
doi = {10.1073/pnas.1715832114},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
issn = {0027-8424},
number = 2,
volume = 115,
place = {United States},
year = {2017},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record at 10.1073/pnas.1715832114

Citation Metrics:
Cited by: 5 works
Citation information provided by
Web of Science

Figures / Tables:

Fig. 1 Fig. 1: A schematic representation of a two-layer CNN with input x, output y, and feature maps z1 and z2. Arrows represent convolutions with nonlinear activation.

Save / Share:

Works referenced in this record:

Superparsing: Scalable Nonparametric Image Parsing with Superpixels
journal, October 2012

  • Tighe, Joseph; Lazebnik, Svetlana
  • International Journal of Computer Vision, Vol. 101, Issue 2
  • DOI: 10.1007/s11263-012-0574-z

PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation
journal, March 2012


Densely Connected Convolutional Networks
conference, July 2017

  • Huang, Gao; Liu, Zhuang; Maaten, Laurens van der
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2017.243

Deep Residual Learning for Image Recognition
conference, June 2016

  • He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • DOI: 10.1109/CVPR.2016.90

Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

Fully Convolutional Networks for Semantic Segmentation
journal, April 2017

  • Shelhamer, Evan; Long, Jonathan; Darrell, Trevor
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, Issue 4
  • DOI: 10.1109/TPAMI.2016.2572683

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
conference, December 2015

  • He, Kaiming; Zhang, Xiangyu; Ren, Shaoqing
  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • DOI: 10.1109/ICCV.2015.123

Semantic object classes in video: A high-definition ground truth database
journal, January 2009


Generalizing the Hough transform to detect arbitrary shapes
journal, January 1981


Radio frequency interference mitigation using deep convolutional neural networks
journal, January 2017


Caffe: Convolutional Architecture for Fast Feature Embedding
conference, January 2014

  • Jia, Yangqing; Shelhamer, Evan; Donahue, Jeff
  • Proceedings of the ACM International Conference on Multimedia - MM '14
  • DOI: 10.1145/2647868.2654889

Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique
journal, July 2001

  • Yongbum Lee, ; Hara, T.; Fujita, H.
  • IEEE Transactions on Medical Imaging, Vol. 20, Issue 7
  • DOI: 10.1109/42.932744

ImageNet: A large-scale hierarchical image database
conference, June 2009

  • Deng, Jia; Dong, Wei; Socher, Richard
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • DOI: 10.1109/CVPR.2009.5206848

What is the best multi-stage architecture for object recognition?
conference, September 2009

  • Jarrett, Kevin; Kavukcuoglu, Koray; Ranzato, Marc' Aurelio
  • 2009 IEEE 12th International Conference on Computer Vision (ICCV)
  • DOI: 10.1109/ICCV.2009.5459469

    Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.